EXP PSYCH FINAL 8,9,10,11 TERMS & QUESTIONS & CONCEPTS

Lakukan tugas rumah & ujian kamu dengan baik sekarang menggunakan Quizwiz!

the unsystematic variability among the members of a group in an experiment.

noise

Regression in Popular Press Articles

"Controlled for" "Taking into account" "Correcting for"

When authors of a research article are describing just the results of a factorial study, which of these terms would you not expect to see?

"Correlation" is not a term used in describing the results of a strictly factorial study, though it may be used within the same article.

To achieve a goal of 20 observations per cell in a 2 × 2 × 3 mixed experiment with the first two factors run within groups and the last factor run between groups, what would be the number of participants needed?

- 60 If this was just a 2 × 2 within-groups design, it would need just 20 participants. Adding the third between groups factor makes 60 necessary: 20 for each level.

Within-Groups Factorial Designs

- both independent variables are manipulated as within groups. - in a 2x2 there is only one group of participants who participate in all four combinations

Results of Strayer and Dweyer's studies

- effect of talking on a cell phone did not depend on age. Older drivers did tend to brake more slowly than younger ones, consistent with past research on aging drivers. -the effect of using a cell phone did not differ with age = cell phone use did not interact with age.

Spreading interaction

- lines not parallel, do not cross over ( treat and no treat/ say something and say nothing) - one line flat, one line increase or decrease but never cross

Independent Groups Factorial Designs

-both independent variables are manipulated as independent groups - in a 2x2 there are four independent groups

Crossed Factorial Design

-factorial design where researchers cross the two independent variables and study each possible combination of the independent variables.

A recent study (Koordeman et al., 2011), conducted in the Netherlands, on the effects of commercials for alcohol or alcohol consumption in the movie theater, found that young adults who consume large amounts of alcohol each week are influenced by the commercials, whereas young adults who consume small amounts of alcohol each week were not influenced. Participants saw one of two types of beverage commercials: alcoholic or nonalcoholic. Their consumption of alcohol during the movie was then measured. Finally, they completed a questionnaire on their drinking habits. What type of design is this?

-independent-groups factorial

When the effect of variable A depends on variable B, this is an example of what type of effect in a factorial design?

-interaction effect

When we are interested in just a simple difference (do the levels in one IV differ from each other), i.e., an overall effect of an IV on the DV, ignoring the other IV, what are we interested in?

-main effect

Mixed Factorial Designs

-one independent variable is manipulated as independent groups and the other is manipulated within groups - i.e. old and young group, each group drove with and without cellphone condition -strayer and and drews

Factorial Designs Can Test Limits

-test whether IV affects different kinda of people, or people in different situations, in the same way. -would cell phone use while driving only affect one age group? or have same effect on people of different ages? -function as form of external validity: testing whether effect generalizes (when IV effects groups in the same way. suggests effect generalizes to all) -Interactions show moderators - Test Theories

What differences need to be investigated when a three-way design is used?

-three main effects, three two-way interactions, and a three-way interaction

How is this shown with graphs?

-two graphs

be able to describe the number of cells in a factorial experiment from a notation, and vice versa

...

Understand the idea of levels of an independent variable. Be able to recognize these levels from a presented experiment.

...

mediator

...

moderator

...

pre-test & post-test independent group design

...

third variable

...

• Be able to calculate marginal means and difference in differences, and know the relationship between "difference in differences" (or, in the case of a three-way interaction a "difference in the difference of differences") and interaction

...

• Be able to calculate the number of participants needed based on the notation of the design and the knowledge of the type (fully between-subjects, fully within-subjects, mixed-factorial design)

...

• Be able to evaluate the four validities in quasi-experimental and above-named small-N designs

...

• Be able to explain the characteristics of a multivariate regression design

...

• Be able to graph an interaction, and to describe the interaction in words

...

• Be able to identify and know the characteristics of the following designs

...

• Be able to interpret the effect of your predictor or independent variable on your dependent variable while also controlling for potential third variables

...

• Be able to relate every type of validity to longitudinal, multivariate regression, and experimental designs. For instance, you should be able to question any type of design using the four validities

...

• Construct Validity

...

• External Validity

...

• Factorial Designs, two - and three-way interactions

...

• From a notation, be able to identify the number of main effects and number of two and three-way interaction effects

...

• In any factorial design, be able to name the independent variables and identify the levels of each independent variable

...

• Internal Validity

...

• Interrupted time-series design

...

• Know and be able to explain the four types of validity

...

• Know and be able to explain the three causal rules and how they relate to experimental design

...

• Know and be able to recognize and explain the characteristics of an independent variable, dependent variable, and confound.

...

• Know and be ready to explain the characteristics of a mediator, moderator, and third variable. Be able to tell the difference between the three

...

• Know the characteristics of the following small-N designs: stable-baseline designs, multiple-baseline designs, and reversal designs

...

• Know the characteristics of the following types of simple experiments (examples from notes):

...

• Know the different variations of a factorial design: fully between-subjects, fully within-subjects, mixed-factorial design

...

• Know the relationship between interaction, moderator, and external validity

...

• Nonequivalent control group design

...

• Nonequivalent groups interrupted time-series design

...

• Quasi-experimental designs and small-n designs

...

• Read a regression table with multiple predictors

...

• Statistical Validity

...

• Understand a cross-lagged design (I sometimes referred to it as a cross-lagged panel model) and understand what each path tells you. Below, I pasted an example from the notes. When you study, play around with changing each path to non-significant or significant and decide how it affects the interpretation

...

• Understand the components of factorial designs: main effects marginal means and interaction effects

...

• Understand what is matching (an alternative to random assignment) and when you would use it.

...

• Understand what it means to "covary" or to "control" for a variable

...

• concurrent measures within-group design

...

• repeated measures within-group design

...

• Be able to recognize, describe, and explain the following threats to internal validity (Chapters 9 & 10)

1. Design confounds. 2. Order effects. 3. Selection effects. 4. Maturation. 5. History. 6. Attrition. 7. Regression to the mean. 8. Instrumentation. 9. Testing. 10. Observer bias. 11. Experimental demand. 12. Placebo effects.

longitudinal design

1. Covariance . Signiﬁcant relationships in longitudinal designs help establish covariance. When two variables are signiﬁcantly correlated (as in the cross-sectional correlations in Figure 9.1), there is covariance. 2. Temporal precedence . A longitudinal design can help researchers make infer-ences about temporal precedence. Because each variable is measured in at least two different points in time, they know which one came ﬁrst. By com-paring the relative strength of the two cross-lag correlations, the research-ers can see which path is stronger. If one of them is stronger (as in the TV/aggression example), the researchers move a little closer to determining which variable comes ﬁrst, causing the other. 3. Internal validity . When conducted simply—that is, by measuring only the four key variables (Time 1 and Time 2 of the two key variables)—longitudi-nal studies do not help rule out third variables. For example, the Eron study cannot clearly rule out the possible third variable of sensation seeking, the desire to engage in risky or dangerous activities. Kids who are higher in sensation seeking would probably have preferred violent TV shows as third graders and might also have acted more aggressively in thirteenth grade. The study design Eron and his colleagues used does not rule out this possibility.

• Understand that only a true experiment can fulfill the three causal rules and know why this is so

1. Covariance of cause and effect. 2. Temporal precedence . 3. Internal validity .

2 x 2

A design where there are two independent variables and each one has two levels.

2 x 2 factorial design. Four cells in this design

A design in which there are two levels of the first independent variable, two levels of the second, and two levels of the third

2 x 2 x2 factorial design. Eight cells in this design

A design in which there are two independent variables, but one has two levels and the other has three levels

2 x 3 factorial design. Six cells in this design

# of Main Effects = ____; # of marginal means you need to compare to find main effects =___.

2;2.

How many independent variables and how many cells are there in a 2 × 3 × 4 study?

3 independent variables, 24 cells

How many main effects? How many two-way interactions?

3 main effects (A, B, C) -3 two-way interactions (A*B, A*C, B*C)

_______ is an extra dependent variable that can be used to help researchers quantify how well an experimental manipulation worked.

A manipulation check

You have a 2x2x4 factorial design. How many IVs? How many levels for each IV?

3-IVs 16-Levels

Compute the difference of the differences:

3.5

TV violence early related to aggression later. Aggression early not related to TV violence later. Suggests that early exposure to violence is related to later aggression.

3rd Grade Aggression & College TV Violence, _r=.01 3rd Grade TV Violence & College Aggression_r=.31*

Aggression and violent TV related in 3rd grade, but not in college.

3rd Grade, Aggression_r=.21* College, Aggression_r=.05

- 2 independent variables - 3 levels of one IV, 4 levels of the other - 12 conditions

3x4 factorial design example

A researcher wants to run a 2 x 3 mixed factorial design. The first factor is within-subjects. The second factor is between-subjects. If the researcher wants 20 observations per cell, how many participants will he need in total?

Yan and Sengupta examined he effects of price, attractiveness and consumer on the perceived tastiness and expensiveness of a dish of fried rice. The study was a 2 x 2 x 2 design that varied price (inexpensive or expensive), picture (attractive or unattractive), and consumer (self or classmate) in a between-subjects design. How many cells are there in this study?

The correclation between amount of caffeine consumed and nervous behavior was found to be 0.30 what conclusion can be drawn from this finding?

9% of the vaiability in nervous behavior can be accounted for by variability in amount of caffeine consumed

What is a bivariate correlation and what type of claim is usually made from them

A bivariate correlation is an association between two variables. Associational claims are made from bivariate correlations.

history

A city in California has asked Professor Rodriguez to conduct an experiment on earthquake preparedness. Professor Rodriguez will assess the preparedness of a random sample of residents in the city and the city will mail out their annual brochure on earthquake safety. Then, two weeks later, he will again assess the preparedness of those residents. Right after the brochures are mailed, a large earthquake is reported in Japan. What threat to internal validity does this pose?

__________ is a simple study that uses a separate group of participants that is generally completed before conducting the study of primary interest in order to confirm the effectiveness of a manipulation.

A pilot study

1. Design confounds

A second variable that unintentionally varies systematically with the independent variable. Example:From Chapter 10 : If pasta served in a large bowl appeared more appetizing than pasta served in a medium bowl. ?: Did the researchers turn nuisance variables into control variables, for example, keeping the pasta recipe constant?

9. Testing

A type of order eﬀect: An experimental group changes over time because repeated testing has aﬀected the participants. Subtypes include fatigue effects and practice eﬀects. Example: A classroom 's math scores improve only because the students take the same version of the test both times and therefore are more practiced at posttest. ?: Did the researchers have a comparison group take the same two tests? Did they use a posttest-only design, or did they use alternative forms of the measure for the pretest and posttest?

Power is defined as the probability of A) Rejecting Ho when it is supposed to be rejected B) Rejecting Ho when it is not supposed to be rejected C) Retaining Ho when it is supposed to be rejected D) Retaining Ho when it is not supposed to be rejected

A) Rejecting Ho when it is supposed to be rejected

When we speak about error variance in the independent groups analysis of variance we are speaking of: A) differences among subjects in the same group B) differences between subjects in different groups C) the overall variability of scores in the experiment D) an error in coding the data

A) differences among subjects in the same group

In a 2 x 4 independent-groups factorial design, how many independent variable are there? a. 2 b. 4 c. 6 d. 8 e. 10

A. 2

The mathematical way to describe an interaction is: a. a difference in differences b. a caveat c. A qualified main effect d. a patterned pattern e. all of the above

A. a difference in differences

main effect of role, no effect of others present, and an interaction

After reading a report by Rockoff (2010), Yingying is studying the effects of others present and their roles on the rate of gambling bets using a simulated slot machine. Her levels of others present are one, two, or six. Her levels of roles are gamblers and observers. She constructs a 2 × 3 table of her results of average time between bets. There are two rows for the roles and three columns for the others present. The values in the first row are 10, 20, and 20 and in the second row are 20, 10, and 10. Describe her results.

Longitudinal Designs 2

Aggression is consistent/persistent, but amount of time watching violence is not. TV Violence 3rd,College_r=.05 Aggression 3rd,College_r=.38*

5. History

An experimental group changes over time because of an external factor or event that aﬀects all or most members of the group. Examples: Dormitory residents use less air conditioning in November than September because the weather is cooler. ?: Did the researchers include a comparison group that had an equal exposure to the external event but did not receive the treatment?

8. Instrumentation

An experimental group changes over time, but only because repeated measurements have changed the quality of the measurement instrument. Examples: Coders get more lenient over time, so the same exact behavior is coded as less rambunctious at post-test than at pretest. ?:Did the researchers train coders to use the same standards when coding? Are pretest and posttest measures demonstrably equivalent?

6. Attrition

An experimental group changes over time, but only because the most extreme cases have systematically dropped out and their scores are not included in the post test. Examples: Because the most rambunctious boy in the cabin leaves camp early, his disruptive behavior aﬀects the pretest mean but not the post test mean. ?: Did the researchers compute the pretest and post test scores with only the ﬁnal sample included, removing any dropouts data from the pretest group average?

4. Maturation

An experimental group improves over time only because of natural development or spontaneous improvement. Example: Rambunctious boys settle down as they get used to the camp setting. ?: Did the researchers use a comparison group of boys who had an equal amount of time to mature but who did not receive the treatment?

7. Regression to the mean

An experimental group whose average is extremely low (or high) at pretest will get better (or worse) over time, because the random events that caused the extreme pretest scores do not recur the same way at post test. Examples: A group's average is extremely depressed at pre-test, in part because some of the people volunteered for therapy when they were feeling much more depressed than usual. ?:Did the researchers include a comparison group that was equally extreme at pretest but did not receive the therapy?

10. Observer bias

An experimental group's ratings diﬀer from a comparison group's, but only because the researcher expects the groups ratings to diﬀer. Example: The researcher expects a low-sugar diet to decrease the campers unruly behavior, so he notices only their calm behavior and ignores the wild behavior. ?:Were the observers of the dependent variable unaware of which condition participants were in? (A comparison group does not automatically get rid of the problem of observer bias.)

instrumentation

As part of an experiment on the effects of behavior modeling, a set of raters are evaluating the prosocial behavior in a series of videotapes of a class of preschoolers. Initially, the raters were quite strict in their ratings, but after three hours of rating, their criteria had changed. What type of threat to internal validity has occurred?

A randomized 3 groups design is analyzed by using a: A) One sample t-test B) 1-way ANOVA C) Independent group t-test D) Three t-tests

B) 1-way ANOVA

For an independent groups ANOVA, comparing three treatment means with a sample of 9 in each treatment, the F-ratio would have degrees of freedom equal to A) 27 B) 2, 24 C) 2, 27 D) 3, 24

B) 2, 24

Which of the following is LEAST important in determining the size of an f ratio? A) Sum of squares between groups B) Total sums of squares C) Mean square within D) Mean square between

B) Total sums of squares

Reducing error variance decreases the probability of: A) a Type I error B) a Type II error C) rejecting the null hypothesis D) none of these

B) a Type II error

We want to study the mean difference in autonomy between first-born and second-born children. Instead of taking a random sample of children we take a random sample of families and sort the children into 1st and 2nd born. The dependent variable is a measure of autonomy. This experiment would most likely employ A) a one-sample t-test. B) an independent measures ANOVA. C) a dependent t-test. D) an independent t-test

B) an independent measures ANOVA.

Which of the following types of content does not belong in the introduction of an APA style lab report? A) statement of purpose B) descriptive statistical results C) hypothesis D) brief overview of study's procedures E) both B abd D

B) descriptive statistical results

Which of the following is the correct order of information in the results section of a report? A) inferential statistics, descriptive statistics, decision concerning the null hypothesis B) descriptive statistics, inferential statistics, decision concerning the null hypothesis C) decision concerning the null hypothesis, inferential statistics, descriptive statistics D) descriptive statistics, decision concerning the null hypothesis, inferential statistics

B) descriptive statistics, inferential statistics, decision concerning the null hypothesis

A researcher was interested in examining the different levels of aggression shown by college students and prisoners with life sentences. Aggression was measured by surveys. Which analysis should the researcher perform on the mean aggression scores of the groups? A) 1-sample t-test B) independent t test C) ANOVA D) Z-test

B) independent t test

The sampling distribution of F-ratios is A) symmetrical with a mean of 0 B) positively skewed with all values greater than or equal to 0 C) negatively skewed with all values less than or equal to 0 D) symmetrical with a mode equal to 1

B) positively skewed with all values greater than or equal to 0

In the Independent Groups ANOVA, the Mean Square within is A) the variability among the treatment means B) the average variability among the scores within each group C) the numerator of the F-ratio D) an indication of the influence of the independent variable

B) the average variability among the scores within each group

To increase power, the easiest variable to control in designing an experiment is usually: A) the difference between the population means B) the sample size C) the sample standard deviation D) the shape of the distribution

B) the sample size

In the preceding question on autonomy in children, we would be most likely to use that design, rather than random sampling of children, because A) we want to control for differences in means. B) we want to control for differences in parenting style. C)we expect scores of children in the same family to be unrelated. D)we want to control for differences in age between first and second born children

B) we want to control for differences in parenting style.

Knowledgeable and unbiased observers have generally noted, and studies have reliably shown, that psychotherapy is better than no treatment at all for a person who is seriously depressed. My study on the effectiveness of therapy failed to find a difference. Which of the following is the best conclusion I could make? A) Psychotherapy really is not effective B) My sample size was too large C) My study may have lacked sufficient power to find a difference D) Other psychologists don't know what they are talking about

C) My study may have lacked sufficient power to find a difference

A Type 2 error is defined as A) Rejecting Ho when it is supposed to be rejected B) Rejecting Ho when it is not supposed to be rejected C) Retaining Ho when it is supposed to be rejected D) Retaining Ho when it is not supposed to be rejected

C) Retaining Ho when it is supposed to be rejected

When we reject the null hypothesis in the analysis of variance we can conclude that: A) all of the means are the same B) all of the means are different from each other C) at least one of the means is different from at least one other mean D) only one mean is different from one other mean

C) at least one of the means is different from at least one other mean

The analysis of variance compares: A) the total variance to the variance within groups B) the total variance to the variance between group means C) the variance between group means to the variance within groups D) the variance within groups to the variance among all data points

C) the variance between group means to the variance within groups

Longitudinal Designs 1

Cause must precede effect. How much violent TV and how aggressive?

Longitudinal Designs 3

Cause must precede effect. Cross-lagged designs are only suggestive.

Quasi-experimental design

Characteristics of quasi-experimental design? -no random assignment to treatment conditions -more threats to internal validity e.g. interrupted time series design is a within-subject quasi-experimental design

What is the name for the level of the independent variable that is intended to represent a neutral condition?

Control group

Regression, attrition, and placebo effects are all threats to internal validity that can be addressed by adding a ________ _______.

Comparison Group

Control for Income

Control for something: to rule it out statistically After you take the relationship of income on behavior problems, will there still be a relationship between time allowed for recess and behavior problems?

Eric designs a study to examine drink preferences of university freshmen. He is planning to have all of the freshmen who participate in his study drink a cup of coffee then rate their enjoyment of the coffee, then drink a cup of tea and rate their enjoyment of the tea, and finally drink a cup of milk and rate their enjoyment of the milk. Eric tells Theresa about the plans for his study and she says she is concerned that he could have a problem with order effect in his study. How can Eric fix this problem?

Counterbalancing

When using multiple regression, what is the term for the variable that the researcher is most interested in explaining or predicting?

Criterion

Dr. Joseph thinks that most people are generally trusting of strangers. He did a study at his university in the United States to test this idea, and the results confirmed his hypothesis. Dr. Joseph is discussing the results of this study with a friend who is a psychology researcher in China, Dr. Ming. Dr. Ming thinks that people in Eastern cultures, such as China, are less trusting of strangers in Western cultures, such as the United States. Dr. Joseph and Dr. Ming decide to run a second study where they have a group of participants in China and a group of participants in the United States both complete the task used in Dr. Joseph's study. This second study is an example of ________.

Cultural psychology

_______ is a sub discipline of psychology that is primarily in generalization mode. It examines how cultural contexts shape the way a person thinks, feels, and behaves.

Cultural psychology

What type of validity does counterbalancing help?

Internal Validity

An important reason for using random assignment in a study with independent groups is to: A) prevent any systematic differences between groups on extraneous variables B) be able to generalize to broader populations C) rule out competing interpretations of any differences we find D) (a) and (c) but not (b)

D) (a) and (c) but not (b)

If we test the mean amount that alcoholic subjects drink before and after therapy, and that difference is not significant, this could mean A) the therapy was not effective. B) the sample size was too large. C) the study lacked sufficient power. D) a) and c)

D) a) and c)

All other things being equal, one study will have more power than another study if: A) it has more subjects B) it controls error variance better C) it compares groups that are more extreme D) all of the above

D) all of the above

We are evaluating a method of therapy for extremely underweight adolescents. If we weighed our subjects at the beginning and end of therapy, a difference in weight could mean A) that our therapy worked. B) that people gain weight over time regardless of what we do. C) there was a confounding variable. D) all of the above.

D) all of the above.

Between-groups variance may reflect: A) chance B) the treatment C) a confound D) all of these

D) all of these

Variance in an experiment may be due to: A) chance B) the independent variable C) a confound D) all of these

D) all of these

When we are worrying about power we are most concerned with: A) a Type I error B) a Type II error C) failing to reject the null hypothesis D) both B and C

D) both B and C

Which of the following statistical results contains an error? A) t(19) = 3.20, p<.05 B) f(2,27) = 1.92, p > .05 C) z = 2.9, p < .05 D) f(0, 27) = 2.85, p <.05

D) f(0, 27) = 2.85, p <.05

The Third Variable Problem

DV=Behavior Problems IV=Time Allowed For Recess r=-.55

) Which of the following are reasons why we might use a repeated measures design? A) It requires too many subjects. B) It is more likely to reject a null hypothesis than the design with different subjects in the groups. C) Information the subjects pick up in early trials may influence their performance on later trials in ways that we don't find helpful. D) It is a more powerful design than an independent groups design E) Both B and D

E) Both B and D

The primary purpose of the methods section is to A) provide sufficient information to allow a replication of the study B) describe the statistical methods use to analyze the data C) relate the purpose of the present study to prior research D) provide a methodological critique of the study E) all are true except C

E) all are true except C

The terms "standard error of the mean, "standard error of the difference between two mean", and "standard error of the difference" are alike in that A) they are measures of sampling error B) they are standard deviations of hypothetical sampling distributions C) their values increase as sample size decrease D) their values are denominators in their respective t-tests E) all of the above are true.

E) all of the above are true.

Which of the following does not belong in the discussion section of a report? A) descriptive statistics B) literature review C) description of participants D) discussion of materials used E) all of the above do not belong

E) all of the above do not belong

The numerator in all F-ratios is A) the Mean Square within B) the Mean square between groups C) an estimate of inherent variability in the raw score population D) variability due to the effect of the treatment (if there is an effect) E) both B and D

E) both B and D

In ANOVA, if the null hypothesis is false, we would expect the obtained F ratio A) to be smaller than the critical F B) to not fall in the region of rejection C) to have a value higher that 1 D) to occur by chance less than p = .05 E) both C and D are true

E) both C and D are true

maturation

Emma is planning an experiment on the effects of being read to on vocabulary size in toddlers. She plans to measure the vocabulary size of a group of 18-month-olds, read to them three times a week for a month, then measure the vocabulary size again. What threat to internal validity should she be concerned about?

Can't think of (and measure)

Every third variable

Lack of which type of validity does not disqualify a studies findings if the study fulfills all other validities?

External Validity:

Which of these is NOT a potential drawback of a within-groups design?

Extraneous differences are held constant across conditions.

• Covariance

From the study's results, we already know deep conversations are associated positively with well-being. As the percentage of deep conversation goes up, well-being goes up, thus showing covariance of the proposed cause and the proposed effect.

What is the relationship between moderators and external validity?

Generalizability is affected by moderators, could suggest that your association does not generalize to all groups of people

Why Not Just Do an Experiment?

Good experiments are the only way to establish causation. Ethics Practicality

Gucciardi and Dimmock (2008) reported on an experiment on choking under pressure in skilled golfers. They varied anxiety level and putting condition in a 2 × 3 within-group design. Anxiety level (low or high) was varied with a competition with financial compensation being introduced following the low anxiety-level performance. The putting conditions were thinking of cue words about putting technique, thinking of irrelevant cue words, and thinking about a single swing thought such as "smooth." Mean distance from hole was computed for the 10 putts in each condition. How many cells was each golfer in?

What represents a null hypothesis?

Ho: u=0

Multiple regression

How can we rule out a third variable in a correlational design study? -measure that 3rd variable and include it in your multiple regression analysis as a control (if relationship is still significant after controlling for CV, then you can be confident that it was not the third variable causing the relationship)

3 independent variables, 24 cells

How many independent variables and how many cells are there in a 2 × 3 × 4 study?

Interaction

How two independent variables are related, whether one depends on the other. - difference in differences = the effect of one independent variable on the dependent variable depends on on the level of the other independent variable

precision

In an experiment on improving children's handwriting, two different techniques of improving handwriting and a control condition are used. Using a pretest/posttest design, both groups who received the treatment showed more improvement than the control group. However, the two groups didn't show any difference from each other. The researcher believes that there is a difference, but that the 5-point assessment scale of handwriting cannot detect it. What measurement problem is the researcher concerned with?

The following graph shows this kind of effect

Interaction effect

...

Is there covariance? Yes. Many studies have shown that the correlation between watching violent TV shows and acting aggressively is moderately strong, around r = .35 (e.g., Paik & Comstock, 1994). These two variables are clearly related. ■ Is there temporal precedence? A typical correlational study cannot establish temporal precedence. In some early studies on TV viewing and aggressive behavior, researchers measured aggressive behavior at the same time as TV preferences. Such a study does not show which one comes ﬁrst. It is pos-sible that watching violent TV shows comes ﬁrst and causes people to be more aggressive. It is also possible, however, that a person's aggressiveness comes ﬁrst and affects his or her TV viewing habits. (In other words, aggressive people choose to watch more violent TV shows, and less aggressive people choose to watch less violent ones.) ■ Is there internal validity? The association between TV violence and aggressive behavior might potentially be explained by a third variable, such as a personality trait. Perhaps people who seek extreme emotional situations (known as sensation seekers) are more likely to both act aggressively and prefer violent TV shows. In this explanation, sensation seeking comes ﬁrst and causes both aggressive behavior and a preference for violent shows. Or perhaps the third variable is gender: Men are both more likely to watch violent shows and more likely to act aggressively than women.

regression

Jared is conducting an experiment with ESP (extrasensory perception) training. He begins with a pretest of his 40 participants and divides them into two groups based on their scores. The participants with the 10 lowest scores are given extensive training on how to detect the signals. The participants with the 30 highest scores are given no training. Both groups are retested and the average score of the participants with the training improved, while the average score of the participants without the training actually fell. What threat to internal validity should Jared consider?

demand characteristics

Job-rating experiment

What type of research design involves measuring the same variables, for the same people, across different time points?

Longitudinal

Longitudinal Designs Summary

Longitudinal designs can rule out some explanations because of temporal precedence. Longitudinal designs do not establish causality because they do not rule out alternative explanations (internal validity)

In an experiment, researchers:

Manipulate one variable and measure another

maturation threats

Many threats to internal validity are corrected for by adding a comparison group. Which of these is not one of the main threats to internal validity that occur even in designs with a clear comparison group?

Is this an example of a mediator or moderator? researcher finds that the relationship between media exposure and self-esteem is stronger for females than for males

Mediator

What kind of third variable explains the relationship between two other variables?

Mediator

What is a mediator variable?

Mediator is a mechanism for a relationship between two variables. Why are these two variables correlated? Keyword: "because" of this mediator variable. Mediators - third variables that are potentially the "mechanism" or the driving effect that explains A and C No different than any third variable, but the researcher can make a story out of it

When a relationship between two variables depends on the level of a third variable, that kind of third variable is called a _________?

Moderator

The effectiveness of fines on water conservation was tested at 3 different cities suffering from a drought. Two cities instituted fines at different times and a third city did not institute fines. Water consumption data for the three years before the onset of the fines was used as baseline and subsequent consumption data was gathered through the end of the drought. Effectiveness of fines was assessed by examining consumption the following month. With regard to the monitoring of water consumption, what type of design was this?

Multiple baseline

The relationship between recess and behavior problems:

Negative (recess mins. go up, behavior problems go down) even when lunch eligibility is controlled for.

Regression Does Not

Not (definitively)Establish Causation

testing

On the first midterm exam in an introductory psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cellphones from her class between the first midterm and the second midterm. When she compares the scores on the two exams for the people who had been using computers and cellphones, she finds a significant improvement on the second exam. Professor Mitchell points out that in her classes, students always do better on the second exam because they are more used to taking her tests. What threat to validity is she suggesting?

instrumentation

On the first midterm exam in an introductory psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cellphones from her class between the first midterm and the second midterm. When she compares the scores on the two exams for the people who had been using computers and cellphones, she finds a significant improvement on the second exam. Professor Mutola looks back over the second exam and begins to wonder if it was just an easier exam. What threat to internal validity is she considering?

attrition

On the first midterm exam in an introductory psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cellphones from her class between the first midterm and the second midterm. When she compares the scores on the two exams for the people who had been using computers and cellphones, she finds a significant improvement on the second exam. She then compares scores for the other students in the class and finds less of an improvement. Which of these threats should she still consider?

one-group, pretest/posttest

attrition

On the first midterm exam in an introductory psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cellphones from her class between the first midterm and the second midterm. When she compares the scores on the two exams for the people who had been using computers and cellphones, she finds a significant improvement on the second exam. When Professor Mutola rechecks her data, she finds that the five multitasking students with the lowest scores on the first exam have dropped the class. What threat to internal validity is this?

Nested Factorial Design

One independent variable in primary, and the other indpendent variable is nested under it i.e. researcher studies two school districts and then three schools within each district (district is first IV and three schools are second, nested, IV)

Maturation, history, regression, attrition, testing, and instrumentation threats are all due to the ______, _____/_____ design while observer bias, demand characteristics, and placebo effects could occur in any experiment.

One-group, pretest/posttest

11. Experimental demand

Participants guess what the study's purpose is and change their behavior in the expected direction. Example: Campers guess that the low-sugar diet is supposed to make them calmer, so they change their behavior accordingly. ?: Were the participants kept unaware of the purpose of the study? Was it an independent-groups design, which makes participants less able to guess the study 's purpose?

What type of interaction is this?

Participants were asked to report how jealous they would be if their partner had an affair. Researchers found that the interaction between participant marital status (married/single) and gender (m/f) on jealousy depends on the type of affair (emotional/physical infidelity).

What is it called when researchers investigate causality by using a variety of correlational studies that all point in a single, causal direction?

Pattern and Parsimony

What are three main disadvantages on within-groups?

Repeated-measures designs have the potential for order effects, which can threaten internal validity. Within-Groups design might not be possible or practical. People can see all levels of the independent variable and then change the way they would normally act.

A friend looks at these data and says, "the only reason French rap predicts violence is because the kids who listen to rap music are just more into violent media in general. I bet they watch more violent TV and stuff like that."

Reply:This challenge question moves students toward applying multiple regression to the third variable problem. Students should reply that your friend is wrong—the relationship between French rap and violence is still significant, even when controlling for exposure to violent media. This result rules out exposure to violent media as a third variable.

Participants in a research study are given a list of words to study for 3 minutes and then, following a delay, are asked to recall the list. The length of the delay is manipulated between participants to be either 2 minutes, 5 minutes, or 10 minutes. Since different groups need different amounts of time, the first 25 participants who arrive are assigned to the 10-minute group, the next 25 are assigned to the 5-minute group, and the final 25 are assigned to the 2-minute group. What confound does this create?

Selection effect

Emma is planning an experiment whether reading to children increases their vocabulary size. She plans to measure the vocabulary size of a group of 18-month-olds, read to them three times a week for three months, then measure their vocabulary size again. How could Emma change the design to remove a major threat to internal validity?

She could add a comparison group

Dr. Robinson designs an intervention that is meant to reduce college students' risky sexual decisions. She hypothesizes that shaming college students about their risky sexual decisions will improve their decision making. She recruits participants and randomizes them to two conditions-the intervention group and the control group. The sexual behavior of all participants is measured in a interview with Dr. Robinson. After the pretesting, participants who are randomized to the intervention group are scheduled for an individual shaming session with Dr. Robinson. The control group does not participate in the shaming session. One week after the intervention, both groups are interviews with Dr. Robinson about their sexual behavior over the past week. She finds that the intervention group reported less risky sexual decisions during the posttest interview. How could Dr. Robinson improve the internal validity of her study?

She could make it a masked design

2. Order effects

Sometimes, being exposed to one condition changes how participants react to the other condition. this happens when exposure to one level of the independent variable inﬂuences responses to the next level of the independent variable. Example: From Chapter 10 : All participants in a bonding study play with their own toddler, followed by a diﬀerent toddler. ?: Did the researchers counterbalance the orders of presentation?

Multiple Regression

Statistical procedure that allows 2 or more independent variables and 1 dependent variable. IV is often called a predictor in multiple regression. DV is often called a criterion.

Statistical significance

Statistical significance p-value is the probability that the effect is due to chance, if the null is true by convention we use p<.05 (sometimes indicated in tables by an asterisk *) large sample size more likely to reach significance

items recalled

The Ranschburg effect in short term-memory involves repeated items: if they are close together in a list, recall is facilitated; if they are far apart, recall is impaired. Francis designs an experiment on this effect using three conditions for a 12 animal names list: no repetition, repetition of the third animal as the fifth item, and repetition of the second animal as the tenth item. Each item is viewed for one-second, then participants recall them in order. Ten participants are tested in each condition. What is the dependent variable?

change the design to be within-groups

The Ranschburg effect in short-term memory involves repeated items: if they are close together in a list, recall is facilitated; if they are far apart, recall is impaired. Francis designs an experiment on this effect using three conditions for a 12 animal names list: no repetition, repetition of the third animal as the fifth item, and repetition of the second animal as the tenth item. Each item is viewed for one-second, then participants recall them in order. Ten participants are tested in each condition. The study showed null effects, and large individual differences in the groups. What is a likely solution?

add more participants

The Ranschburg effect in short-term memory involves repeated items: if they are close together in a list, recall is facilitated; if they are far apart, recall is impaired. Francis designs an experiment on this effect using three conditions for a 12 animal names list: no repetition, repetition of the third animal as the fifth item, and repetition of the second animal as the tenth item. Each item is viewed for one-second, then participants recall them in order. Ten participants are tested in each condition. The study showed null effects, and large variability within the groups. What is a likely solution?

attrition

repetition condition

• Temporal precedence (because IV always comes before DV)

The causal variable must precede the effect variable; it must come ﬁrst in time

Gucciardi and Dimmock (2008) reported on an experiment on choking under pressure in skilled golfers. They varied anxiety level and putting condition in a 2 × 3 within-group design. Anxiety level (low or high) was varied with a competition being introduced following the low-anxiety trials. The putting conditions were thinking of cue words about either putting technique or irrelevant items, or a single swing thought such as "smooth." Mean distance from hole was computed for the 10 putts in each condition. The main effect for anxiety was not significant. What does this mean about the marginal means?

The marginal means for the two anxiety conditions are not significantly different. -Marginal means are used to inspect the main effects, and in the case of a not significant main effect of anxiety, they are very close to each other.

• Be able to explain the relationship between these causal rules and multivariate, longitudinal, and experimental designs

The negative association between deep talk and well-being could be attributable to some third variable that is connected to both deep talk and well-being. For instance, a busy, stressful life might lead people to both report lower well-being and have less time for substantive conversa-tions. Or perhaps in this college sample, having a strong college-preparatory background is associated with both deep conversations and having higher levels of well- being in college (because those students are more prepared). But be careful—not any third variable will do. The third variable, to be plausible, must correlate logically with both of the measured variables in the original as-sociation. (For example, we might propose that income is an alternative expla-nation, arguing that people with higher incomes will have higher well-being. For income to work as a plausible third variable, though, we would have to explain how higher income is related to more deep talk, too.)

ceiling effect

The students in 50-student introductory psychology class were randomly assigned to one of two review sessions, each being taught with a different technique. The next day, every student got all 10 of the test questions correct. What problem does Professor Zhao have in determining the better teaching technique for review sessions?

• Temporal precedence

The study measured deep talk and well-being during the same, short time period, so we cannot be sure whether an increase in deep talk came ﬁrst, followed by an increase in well-being, or whether people were happy ﬁrst and then engaged in more deep conversations.

• Covariance (if you get group differences)

There must be correlation, or association, between the cause variable and the effect variable

• Internal validity via randomization or counterbalancing

There must be no plausible alternative explanations for the relationship between the two variables.

Why do researchers conduct studies with factorial designs?

To test whether an independent variable affects different kinds of people, or people in different situations, in the same way

Participant Variable

Variable whose level are selected (measured) and not manipulated i.e. age, sex, ethnicity, and culture - not truly independent variables

Factorial designs

We are always interested in the main effect for each IV and the interaction effects among pairs of our IVs. If we have 4 IVs, how many main effects do we look at? -main effect of A -main effect of B -main effect of C -main effect of D

Gucciardi and Dimmock (2008) reported on an experiment on choking under pressure in skilled golfers. They varied anxiety level and putting condition in a 2 × 3 within-group design. Anxiety level (low or high) was varied with a competition being introduced following the low-anxiety trials. The putting conditions were thinking of cue words about either putting technique, irrelevant items, or a single swing thought such as "smooth." Mean distance from hole was computed for the 10 putts in each condition. What are all the differences that must be examined?

What are all the differences that must be examined? -two main effects and one interaction There are two independent variables, so there are two main effects and one interaction possible, even though one variable has three levels. How many cells was each golfer in? -6

Experimental Design

What are the pros of such a design? -more control over confound variables. (associational designs in contrast can only statistically control for third variables that are measured).

a no-treatment/no-placebo group

What should be added to a double-blind placebo control study to demonstrate that the placebo had an effect?

internal validity and construct validity

What two types of validity in an experiment can observer bias threaten?

correlation

When authors of a research article are describing just the results of a factorial study, which of these terms would you not expect to see?

12. Placebo effects

When the control group is exposed to an inert treatment such as a sugar pill.Participants in an experimental group improve only because they believe in the eﬃcacy of the therapy or drug they receive. Example: Women receiving cognitive therapy improve simply because they believe the therapy will work for them. ?:Did a comparison group receive a placebo (inert) drug or a placebo therapy?

What is a three-way interaction?

When you have 3 IVs (e.g., 2x3x2) When the interaction between 2 of the IVs depends on the level of the 3rd IV (in other words, when the 2 interactions are different

floor effects

Which of the following is not one of the three most common threats to internal validity?

use a double-blind study

Which of these is not a solution to individual differences as a source of within-group variability?

selection effects

Which of these is not a source of error variance?

large sample size

Which of these is not one of the problems with study design that may cause the study to return a null hypothesis when the independent variable actually does cause a change in the dependent variable?

attrition

Which threat to internal validity occurs when there is a greater systematic loss of participants in one condition than the other condition?

This is the result of multiple regression analysis. How do you interpret these results in words?

X2 is a significant predictor of Y1, p<.05. As X2 increases, Y1 increases, even after controlling for X1.

a two-way interaction between price and consumer

Yan and Sengupta (2011) examined the effects of price, attractiveness, and consumer on the perceived tastiness and expensiveness of a dish of fried rice. The study was a 2 × 2 × 2 design that varied price (inexpensive or expensive), picture (attractive or unattractive), and consumer (self or classmate) in a between-subjects design. A main effect of price and a main effect of picture were found. It was found that the impact of price on tastiness/expensiveness judgments was weaker in the self than in the classmate. What type of interaction does this describe?

a two-way interaction between picture and consumer

Yan and Sengupta (2011) examined the effects of price, attractiveness, and consumer on the perceived tastiness and expensiveness of a dish of fried rice. The study was a 2 × 2 × 2 design that varied price (inexpensive or expensive), picture (attractive or unattractive), and consumer (self or classmate) in a between-subjects design. A main effect of price and a main effect of picture were found. It was found that the picture had a greater impact on tastiness/expensiveness judgments in self than in classmate. What type of interaction does this describe?

all of them are manipulated

Increasing number of independent variables

__ x __ x __ ^ level of each dependent variable - with each additionial variable need to test main effect ( 2x2x2) need to test for three main effects

Factorial Designs

a design in which there are two or more independent variables (aka factors).

The degree to which a quasi-experiment supports a causal claim depends on which of the following: a. Its design and its results b. its duration and its sample size c. its importance and its external validity d. its statistical significance and its practical significance e. all of the above

a its design and its results

Which of the following is an example of a field setting?

a preschool playground with video cameras

Which variable is the mediator in this example:

a researcher is interested in examining whether the effect of work-family conflict on marital satisfaction goes through another variable, emotional exhaustion.

reversal design , as in the other two small- N designs:

a researcher observes a problem behavior both with and without treatment, but takes the treatment away for a while (the reversal period) to see whether the problem behavior returns (re- verses).

A stable-baseline design is:

a study in which a researcher observes behavior for an extended baseline period before beginning a treat-ment or other intervention; if behavior during the baseline is stable, the researcher is more certain of the treatment's effectiveness.

Gucciardi and Dimmock (2008) reported on an experiment on choking under pressure in skilled golfers. They varied anxiety level and putting condition in a 2 × 3 within-group design. Anxiety level (low or high) was varied with a competition being introduced following the low-anxiety trials. The putting conditions were thinking of cue words about either putting technique, irrelevant items, or a single swing thought such as "smooth." Mean distance from hole was computed for the 10 putts in each condition. High anxiety increased distance in the technique condition but not in the other two conditions. What does this describe?

a two-way interaction between anxiety and condition -This wording suggests that the dependent variable was changed by the anxiety manipulation in the technique condition, but not in the other conditions.

Yan and Sengupta (2011) examined the effects of price, attractiveness, and consumer on the perceived tastiness and expensiveness of a dish of fried rice. The study was a 2 × 2 × 2 design that varied price (inexpensive or expensive), picture (attractive or unattractive), and consumer (self or classmate) in a between-subjects design. A main effect of price and a main effect of picture were found. It was found that the picture had a greater impact on tastiness/expensiveness judgments in self than in classmate. What type of interaction does this describe?

a two-way interaction between picture and consumer -This means that in looking at the tastiness/expensiveness ratings for self, there is a larger difference between the attractive and unattractive ratings than there is in those ratings for classmate.

a two-way interaction between price and consumer -This means that in looking at the tastiness/expensiveness ratings for self, there is a smaller difference between the inexpensive and expensive ratings than there is in those ratings for classmate.

What is a moderator?

a variable that moderates the relationship between two other variables shows that the relationship (or effect) is stronger in one group versus another the relationship is different depending on this moderator variable

Which of the following is an association claim? a. "Owning a dog is related to higher life satisfaction" b. "A majority of Americans like dogs" c. "Dog traveled 500 miles to find its owners" d."Being visited by dogs in the hospital causes decreases in recover time" e. None of the above are association claims

a. "Owning a dog is related to higher life satisfaction"

An example in the text hypothesized that 4% of the variability in life expectancy was accounted for by variability in smoking behavior. The values of r and r^2 respectively are equal to a. .20 and .04 b. .04 and .16 c. .04 and .20 d. more information is needed

a. .20 and .04

A researcher is conducting a 2x4 independent-groups factorial design. How many interactions will need to be examined? a. 1 b. 2 c. 3 d. 4 e. 6

a. 1

8. Researchers speculated that the reason bilingualism is associated with later onset of dementia is that bilingual people develop richer connections in the brain through their experiences in managing two languages; these connections help stave off dementia symptoms. This statement describes:

a. A mediator

1. Dr. Weber conducted a long-term study on friendship. He noticed that the most introverted people dropped out by the third session. Therefore, his study might have which of the following internal validity threats?

a. Attrition

1. What is the term for a quasi-experimental design with at least one treatment group and one comparison group, in which the partici-pants have not been randomly assigned to the groups?

a. Nonequivalent control group design

3. What type of design is Max's experiment?

a. Posttest-only design

5. The researchers found that in the two cities that imposed water usage ﬁnes, water use dropped dramatically in subsequent months. Which of the following would be a threat to internal validity in this study?

a. If the cities that imposed ﬁnes also hap-pened to use a public service ad campaign to reduce water usage.

5. Dr. Banks modiﬁes her design and conducts a second study. She used the same number of dogs and the same design, except now she re-warded one group of dogs with miniature hot dogs, and another group of dogs with pieces of apple. She found a big difference, with the mini-hot-dogs group learning the command faster. Dr. Banks avoided a null result this time, because she:

a. Increased the between-groups variability.

1. A headline in Yahoo! News made the following (bivariate) association claim: "Facebook users get worse grades in college" (Hsu, 2009). The two variables in this headline are:

a. Level of Facebook use and college grades.

2. Suppose a researcher uses a longitudinal design to study the relationship between Facebook use and grades over time. She measures both of these variables in Year 1, and then measures both variables again in Year 2. Which of the following is an example of an auto correlation in the results?

a. The correlation between Facebook use in Year 1 with Facebook use in Year 2.

4. Dr. Banks tests to see how many training sessions it takes for dogs to learn to "Sit and stay." She randomly assigns 60 dogs to two reward conditions: one in which the reward is miniature hot dogs, and one in which the reward is small pieces of steak. Surprisingly, she ﬁnds that the dogs in each group learn "Sit and stay" in about an equal amount of sessions. Given the design of her study, what is the most likely explanation for this null effect?

a. The dogs loved both treats (her reward manipulation has a ceiling effect).

5. Which of the following sentences describes a moderator for the relationship between risk taking and liking spicy foods?

a. There is a positive relationship between liking spicy foods and risk taking for men, but no relationship for women.

A researcher wanted to see how watching movies influenced subjects' moods. She measured beta-endorphin levels (a physiological measure of well-being) of subjects following each of 2 movies. Half of the subjects first saw Titanic followed by Schindler's list, while the other half first saw Schindler's list then the titanic. Varying the movie order is an example of a. counterbalancing b. random sampling c. selection bias d. practice effects

a. counterbalancing

Imagine that you are reading a journal article and you see the following sentence: "The study used a 2x4 design" Based on this sentence alone, you would know all of the following pieces of information except: a. The number of participants in the study b.the number of main effects that need to be examined c. the number of interactions that need to be examined d. the number of cells e. the number of independent variables

a. the number of participants in the study

An independent variable is one that: a. is manipulated b. is measured c. is kept constant d. has one level e. none of the above

a. is manipulated

Which of the following is a necessary component of a longitudinal design? a. measuring the same variable at two points in time b. measuring at least four variable at one time c. measuring different age groups at two different times d. manipulating a variable at two points in time e. none of the above

a. measuring the same variable at two points in time

All other things equal, the MSerror in a repeated measures design is ____ than the corresponding MSerror in a between-subjects design a. smaller b. larger c. the same size d. we have no way to predict

a. smaller

The standard deviation of a sampling distribution is known as a. the standard error b. the variance c. error d. the sampling deviation

a. the standard error

What is the advantage of multiple regression?

ability to rule out third variables by measuring multiple IVs and seeing whether they are significant predictors of the DV. -so if you suspect something of being a CV, then measure it and add it into the multiple regression and see if your beta is still significant. your beta may change and become no longer significant (bad).

Frances did a study to investigate the effect of concreteness on memory. She created a list of 12 items that are very concrete (such as pencil and table) and a list of 12 items that are very abstract (such as justice and freedom). Each item was viewed for one second, then participants recalled them in order. Ten participants were tested in each condition. The study showed null effects, and large variability within the groups. What is a likely solution?

add more participants

• Internal validity

addresses the degree to which a study supports a causal claim. Although it is not necessary to interrogate internal validity for an association claim because it does not make a causal statement, it can be tempting to assume causality. third variable problem in associational designs.

Outliers can do what?

affect direction of a relationship affect the strength of a relationship biggest effect (worse) when sample size is small

Koordeman et al. (2011) conducted a study on the effect of alcohol commercials on alcohol consumption in a movie theatre. Participants saw one of two types of beverage commercials: alcoholic or nonalcoholic. Their consumption of alcohol during the movie was then measured. Finally, they completed a questionnaire on their usual drinking habits. Koordeman found that young adults who generally consume large amounts of alcohol each week were influenced to drink more alcohol when they saw alcohol commercials, whereas the alcohol consumption of young adults who generally consume small amounts of alcohol each week was not influenced by the type if commercial shown. Which of the following is a participant variable in this study?

amount of alcohol consumed by the young adult during the week

amount of alcohol consumed by the young adult during the week -The weekly alcohol consumption of the participant was selected, not manipulated.

On the first exam in an introductory Psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cell phones from her class between the first and second exam. When she compares the scores on the two exams, she finds a significant improvement on the second exam. When Professor Mutola rechecks her data, she finds that the five students with the lowest scores on the first exam have dropped the class. What threat to internal validity is this?

attrition

Which threat to internal validity occurs when there is a greater systematic loss of participants in one condition than the other condition?

attrition

Occurs when a certain kind of participant drops out before the end of the study.

attrition threat

occurs when people drop out of the study before it ends, but only a problem when systematic, meaning only a certain type of person drops out (e.g., "maybe a certain kind of people leave the study before the end?"); how to minimize: dropping scores from pretest as well; occurs in a repeated-measures experiment or quasi-experiment

attrition threat (i.e., mortality)

Types of correlations (p.238)

autocorrelation: relationship of a variable with itself over time. -cross sectional: relationship between two variables at the same point in time. -cross lag: relationship between X at one time and Y at a later time.

All of the following are advantages of within-groups designs EXCEPT: a. Participants in the treatment/control groups will be equivalent b. It is less time-consuming for the participants c. It gives researchers more power to find differences between conditions d. They require fewer participants e. All of the Above are advantages of within-groups designs

Suppose that you sell ice cream from a cart on the street. After you pay the ice cream supplier, the regression line that predicts your ice cream profits from the number of house you work has a slope of 15. But the man who owns the car charges you $5 per hour in rent. How much money will you ear per hour? a. 15 b. 10 c. 5 d. nothing

b 10

A 2 x 4 factorial has a. 8 subjects b. 2 levels of one variable and 4 levels of the other c. 8 factors d. one variable with 4 levels and 2 subjects

b. 2 levels of one variable and 4 levels of the other

4. Max randomly assigned people to shake hands either with the "warm hands" experimenter or the "cold hands" experimenter. Why did he randomly assign participants?

b. Because he wanted to avoid selection effects.

Max ran an experiment in which he asked people to shake hands with an experimenter (played by a female friend) and rate the experimenter's friendliness, using a self-report measure. The experimenter was always the same person, using the same standard greeting for all participants. People were randomly assigned to either shake hands with her after she had cooled her hands under cold water, or to shake hands with her after she had warmed up her hands under warm water. Max's results found that people rated the experimenter as more friendly when her hands were warm than when they were cold. 1. Why does Max's experiment satisfy the causal criterion of temporal precedence?

b. Because the participants shook the experi-menter's hand before rating her friendliness.

6. A news outlet reported on a study of people with dementia. The study found that among patients with dementia, bilingual people had been diagnosed 3-4 years later than those who were monolingual. What are the variables in this bivariate association?

b. Being bilingual or not, and age at dementia diagnosis

5. Which of the following questions would be interrogating the construct validity of Max's experiment?

b. How well did Max's "experimenter friendliness" rating capture participants'

A psychologist is working with the parents of four children, all of whom exhibit violent behavior toward one another. The parents were instructed to record the number of violent behaviors each child exhibits in the pre-dinner hour for 1 week. The parents then begin a using positive reinforcement tech-nique to shape the behavior of the youngest child, while continuing to record the behavior of all children. The recording continues and the technique is used on one additional child each week. By the end of 6 weeks, there is a signiﬁcant decrease in violent behaviors for each of the children. What type of design did the psychologist use?

b. Multiple-baseline design

7. The journalist reported that the relationship between bilingualism and age at diagnosis did not change, even when the researchers controlled for level of education. What does this suggest?

b. That the relationship between bilingual-ism and dementia onset is not attributable to the third variable: level of education.

3. A regression threat applies especially:

b. When the researcher recruits a sample whose average is extremely low or high at pretest.

After running a t-test on the mean numbers of jelly beans that men and women eat over the course of the year, I conclude that men eat significantly more jelly beans than women. If men and women actually eat the same number of jelly beans, my conclusion is a. a valid conclusion b. a type I error c. a type II error d. an example of power

b. a type I error

Counter balancing is a technique to a. lower the weight of subjects b. distribute carry-over effects evenly across the data c. increase the power of an experiment d. reduce the likelihood of reasonable conclusions

b. distribute carry-over effects evenly across the data

The number of main effects that need to be examined is ____ the number of independent variables. a. more important than b. equal to c. similar to d. unrelated to e. independent of

b. equal to

Which of the following CANNOT be said of the interaction in a study? a. It can be determined by examining a graph of the results b. it can be determined by investigating marginal means c. It can exist even if the main effects are not significant d. it is almost always more important than a study's main effects. e. there are multiple types of interactions (e.g., crossover interaction).

b. it can be determined by investigating marginal means

A factorial analysis of variance has a. more than on dependent variable b. more than on independent variable c. every level of every independent variable paired with every level of every other independent variable d. both b. and c.

b. more than on independent variable

Dr. Ellison finds a relation between the amount of sleep and problem solving. Specifically, having a higher amount of sleep the night before an exam is associated with higher scores on two measures of problem solving. This is an example of which type of association? a. negative association b. positive association c. zero association d. curvilinear association e. there is not enough information to answer this questions

b. positive association

1. Suppose you hear that conscientious people are more likely to get regular health checkups. Which of the following correlations between conscientiousness and getting checkups would probably support this claim?

b. r= 0.45

Imagine that you are reading a journal article and you see the following sentence: "The study used a 2 x 2 design." Where are you likely to have encountered this sentence? a. the introduction b. the method section c. the results section d. the discussion section e. the references

b. the method section

The major advantage of repeated measures designs is that a. they allow you to use more subjects b. they allow you to remove individual difference from the error term c. they are easier to analyze d. they have a higher probability of a type 2 error

b. they allow you to remove individual difference from the error term

A researcher notices an interaction in his factorial study. In describing this, which statement might he use to explain the link between Independent variable A. and independent variable B in predicting the dependent variable? a. Variable A cancels out Variable B. b. The effect of variable A depends on variable B. c. The effect of variable a is confused by variable b. d. Variable A mainly affects variable B e. the effect of variable A is mediated by variable b.

b.the effect of variable a depends on variable b

In a buisness class experiment on the endowment effect, Theo is comparing the value of a coffee mug to someone who owns it and is selling it to someone who is buying it. The endowment effect describes the tendency of sellers to value something they own more than buyers do. Participants are randomly assigned to be buyers or sellers of a mug with their first name on it. Buyers select the maximum prices they would pay for the mug. Sellers select the minimum price they would accept for the mug. How does Theo control for selection effects?

by using random assignment of particpants

5. Which of the following statements is an example of a mediator of the relationship between Facebook use and college grades?

c. Facebook use and college grades are cor-related because Facebook use leads to less time studying, which leads to lower grades.

3. In the longitudinal study described in question 2, which pattern of cross-lag correlations would indicate that Facebook use leads to lower grades (rather than the reverse)?

c. Grades at Year 1 shows a strong correlation with Facebook use at Year 2, and Facebook use at Year 1 shows a strong correlation with grades at Year 2.

7. Which of these is not a method for maximiz-ing the external validity of the conclusions of a small- N study?

c. Randomly assign people to the treatment and control conditions

4. Consider this statement: "People who use Facebook got worse grades in college, even when the researchers controlled for the level of college preparation (operationalized by SAT scores) of the students." What does it mean?

c. SAT score can be ruled out as a third variable explanation for the correlation between Facebook use and college grades.

2. Which of these associations will probably be plotted as a bar graph rather than a scatterplot?

c. Students at private colleges get higher GPAs than those at public colleges.

2. Which of these is not a reason for a researcher to select a quasi-experimental design?

c. To ensure internal validity.

A correlation was computed between amount of exercise people do and people's overall happiness. A significant correlation was found, such that the more people exercise, the happier they are. What is the best conclusion to draw from this finding? a. exercise leads people to be happy b. we have proved that people should exercise more c. a positive relationship exists between exercise and happiness d. a negative relationship exists between exercise and happiness

c. a positive relationship exists between exercise and happiness

We would like to a. max the power of a test b. min the probability of a type I error c. do both a and b d. max the probability of a type II error

c. do both a and b

Sampling distributions help us test hypotheses about means by a. telling us exactly what the population mean is b. telling us how variable the population is c. telling us what kinds of means to expect if the null hypothesis is true d. telling us what kinds of means to expect the null hypothesis is false

c. telling us what kinds of means to expect if the null hypothesis is true

A simple effect is defined as a. part of the interaction b. the effect of one variable taken by itself c.the effect of one variable at a single level of the other variable d. the difference between the for effect an the column effect

c. the effect of one variable at a single level of the other variable

A researcher decides that instead of conducting a 2x4 independent-groups factorial design, he is going to conduct a 2 x 4 mixed-model factorial design. Which of the following things will change? a. the number of main effects that need to be examined b. the number of interactions that need to be examined c. the number of participants needed d. the number of cells e. all of the above will change

c. the number of participants needed

If we were to repeat an experiment a large number of times and calculate statistic such as the mean for each experiment, the distribution of these statistics would be called a. the distributional distribution b. the error distribution c. the sampling distribution d. the test outcome

c. the sampling distribution

Which r-value represents the strongest correlation? a. +.50 b. -.50 c. -.75 d. 1.65

c.-.75

Occurs when some form of contamination carries over from one condition to the next

carryover effects

may occur when scores are maxed out on high or low end (e.g., giving a math test for stereotype threat, too easy-everyone does equally well showing a ceiling effect, too hard-no one does well showing a floor effect); problem: group score almost the same on the DV; using a manipulation check can help identify

ceiling and floor effect

When all scores are squeezed together at the high end

ceiling effect

Which of the following does NOT contribute to within-groups variablility?

ceiling effect

A study in which researchers study the same research question but use different procedures. At the abstract level, the variables in the study are the same, but the procedures for operationalizing the variables are different

conceptual replication

Roediger and McDermott (1995) conducted a study involving a paradigm initially developed by Deese (1959) which produces false recall of a word when a participant is given a list of words to recall which centers on a particular word but does not include it. For example, if participants were given a list that included sandal, towel, sunscreen, and waves, then they would falsely remember the word beach even though it was not on the list. They did two studies based on Deese's original study. In the first study, they used the same word lists that Deese used and in the second experiment they used new sets of stimulus words. What is the term for the second study they ran?

conceptual replication

Participants are exposed to all the levels of an independent variable at roughly the same time, and a single attitudinal or behavioral preference is the dependent variable

concurrent-measures design

A study's independent variable should not be confused with it's levels, which are also referred to as ________.

conditions

Potential threats to internal validity

confounds

consumer price picture all of them are manipulated <<<

Any variable than an experimenter holds constant on purpose

control variable

When authors of a research article are describing just the results of a factorial study, which of these terms would you NOT expect to see?

correlation

When researchers use ________, they present the levels of the independent variable to participants in different orders.

counterbalancing

Eric designs a study to examine drink preferences of university freshman. He is planning to have all of the freshman who participate in his study drink a cup of coffee then rate their enjoyment of the coffee, then drink a cup of tea and rate their enjoyment of the tea, and finally drink a cup of milk and rate their enjoyment of the milk. Eric tells Theresa about the plans for his study and she says she is concerned that he could have a problem with order effect in his study. How can Eric fix this problem?

counterbalancing-presenting the levels of the independent variable to participants in sequences to control for order effects.

studies each possible combination of the IVs, pairing each level of one IV with each level of the other IVs.

crossed factorial design

A subdiscipline of psychology focusing on how cultural contexts shape the way a person thinks, feels, and behaves

cultural psychology

A researcher is conducting a 2 x 4 independent-groups factorial design. Assuming he wants 25 people in each cell how many participants does the researcher need to recruit? a. 100 b. 125 c. 150 d. 200 e. 250

d. 200

A researcher is conducting a 2x4 independent groups factorial design. How many cells are in the design? a. 2 b. 3 c. 6 d. 8 e. 10

d. 8

2. How is a testing threat to internal validity dif-ferent from an instrumentation threat?

d. A testing threat refers to a change in the participants over time; instrumentation threats refer to a change in the measuring instrument over time.

3. A study found that people who like spicy foods are generally risk takers. Which of the following questions interrogates the construct validity of this correlation?

d. How well did they measure risk taking and liking spicy foods?

4. Darrin reads a story reporting that students at private colleges get higher GPAs than those at public colleges. He wonders if this means going to a private college causes you to have a higher GPA; if so, he'll go to a private college! Applying the three causal criteria, Darrin knows there is covariance here. He also knows there is temporal precedence, because you choose a college ﬁrst, and then you get your GPA. Which of the following questions would help Darrin ask about the third criterion, internal validity?

d. Is there some other reason why these two are related? Maybe better students are more likely to go to private colleges, and they are also going to get better grades?

6. When a study has a large number of partici-pants and a small amount of unsystematic variability (low measurement error, low levels of situation noise), then it has a lot of:

d. Power

2. In Max's experiment described above, what was a control variable?

d. The standard greeting the experimenter used while shaking hands.

In a factorial analysis of vaiace you cannot have a. both a significant interaction and a significant main effect b. two significant main effects c. a significant main effect and a nonsignificant interactions d. none of the above; and combination is possible

d. none of the above; any combination is possible.

Whether or not we reject the null hypothesis depends on a. the probability of the result given the null hypothesis is true b. how far the data depart from what we would expect if the null hypothesis were true c. the size of some test statistic d. all of the above

d. all of the above

Which of the following things can be done to reduce the effect of individual differences? a. using a matched groups design b. using a within groups design c. using a homogenous sample d. all of the above can be done to reduce the effect of individual differences e. nothing can be done to reduce the effect of individual differences

d. all of the above can be done to reduce the effect of individual differences

The major disadvantage with repeated measures designs is that they a. require to many subjects b. are less powerful than between subjects designs c. have a funny looking summary table d. are subject to the influence of carry-over effects

d. are subject to influence of carry-over effects

The difference between a one-way analysis of variance and a factorial analysis of variance is a. the presence of an interaction b. the presence of more than one main effect c. one-way analyses of variance have an error term, whereas factorial analyses do not d. both a and b

d. both a and b

Which of the following is a reason that multiple regression designs are inferior to experimental designs? a. They can only control for third variables that are measured. b. they cannot establish temporal precedence c. they take longer to conduct d. both a and b are true e. all the above are true

d. both a and b

Observer bias can threaten which of the following big validities? a. Internal validity b. external validity c. construct validity d. both a and c c. both a and b

d. both a and c

Which of the following is a within-groups quasi experimental design? a. interrupted time-series design b. nonequivalent control group design c.Nonequivalent groups interrupted time-series design d. both a and c e. all of the above

d. both a and c

In what way does high within-groups variance obscure between-groups variance? a. It leads to smaller effect sizes b. It limits the type of statistical analyses that can be conducted c. it cause more overlap between experimental/comparison groups d. both a and c obscure between-groups variance e. both b and c obscure between-groups variance

d. both a and c obscure between-groups variance

A research was interested in seeing if males or females in large lecture classes fell asleep more during in-class videos. The alternative hypothesis of this study is a. males will fall asleep more than females b.females will fall asleep more than males c. males and females fall asleep at the same rate d. either a or b

d. either a or b

Hypothesis is testing is part of a. descriptive statistics b. order statistics c. test construction statistics d. inferential statistics

d. inferential statistics

Which of the following is NOT a question you should ask about the statistical validity of an association claim? a. what is the effect size? b. is the correlation statistically significant? c. are there subgroups? d. is random assignment affecting the findings? e. could outliers be affecting the relationship?

d. is random assignments affecting the findings?

we want to predict a person's happiness from the following variables:degree of optimism, success in school, and number of close friends. what type of statistical tests can tell us whether these variables predict a person's happiness? a. factorial anova c. multiple comparison c. correlation d. multiple regression

d. multiple regression

This is a problem when participants guess what the study is supposed to be about and change their behavior in the expected direction.

demand characteristics

When an experiment contains cues that lead participants to guess its hypothesis

demand characteristics

cues that lead participants to guess a study's hypotheses; solution: double-blind study

demand characteristics

An experimenter's mistake in designing the independent variable; it is a second variable that happens to vary systematically along with the intended independent variable and therefore is an alternative explanation for the results

design confound

A study in which researchers repeat an original study as closely as they can, to see whether the original effect shows up in the newly collected data

direct replication

In psychology lab, Tatiana is conducting an experiment on depth perception using the Howard-Dolman box. Inside the box are two vertical rods and a horizontal ruler. The participant manipulates the rods until they appear to be aligned at the same distance away, then the experimenter measures how far out of alignment they are. There are three conditions: left eye only, right eye only, and both eyes. Tatiana is using a repeated-measures design. What is the dependent variable in this experiment?

distance out of alignment of the rods

when neither subjects nor experimenter knows who is in each condition.

double-blind study

a study that uses a treatment group and a placebo group and in which neither the research assistant nor the participants know who is in which group; helps rule out placebo effects

double-blind placebo control group studies

A study in which neither the people treating the patients nor the patients themselves know whether they are in the real group or the placebo group

double-blind placebo control study

A study in which neither the participants nor the researchers who evaluate them know who is in the treatment group and who is in the comparison group

double-blind study

Which of the following phrases would indicate that a researcher is making a causal claim? a. curbs b. seems to decrease c. enhances e. all of the above would indicate a causal claim.

e. all of the above

Regression is especially problematic in which of the following situations? a. when on group has an extremely low score at pretest b. when one group has an extremely high score at pretest c. when the experimental and comparison groups are equal at pretest d. both a and b e. all of the above

e. both a and b

Spontaneous remission in clinical studies is an example of which of the following threats to internal validity? a. regression b. attrition c. observer bias d. placebo effects e. maturation

e. maturation

Which of the following is a threat to internal validity found in within-groups designs but not in independent-groups designs? a. Selection effects b. design confounds c. counterbalancing d. demand characteristics e. practice effects

e. practice effects

Characteristics of a small-N experiment?

each person in a small-N design is treated as a separate experiment -when you measure baseline, administer treatment, measure during treatment, then remove the treatment and measure to see if behavior reverts back, this is called a reversal design

A study's similarity to real-world contexts

ecological validity

Researchers manipulate at least one variable and measure another

experiment

When researcher's create settings in which people experience authentic emotions, motivations, and behaviors

experimental realism

In a study, the idea that a meta-analysis might be overestimating the true size of an effect because null effects, or even opposite effects, have not been included in the collection process

file drawer problem

A design in which there are two or more independent variables

factorial design

two or more independent variables examined in one study (most common type of experiment).

factorial design

When a study takes place in the real world

field setting

When all scores cluster at the low end

floor effect

Where all possible condition orders are represented

full counterbalancing

What types of counterbalancing are there?

full counterbalancing: in which ALL possible condition orders are represented. partial counterbalancing: in which only SOME of the possible condition orders are represented.

Dr. Reynolds develops a treatment for social anxiety disorder. After he has shown his treatment to be effective in very controlled laboratory studies, he decides to test it in other settings. He collaborates with clinicians who work in a variety of clinical settings across the country. Dr. Reynolds trains the clinicians on his treatment, but doesn't supervise them closely. He also allows patients with some common comorbidities , such as depression, to participate in the study. This study is in _______.

generalization mode

When researcher's want to generalize the findings from the sample in their study to a larger population

generalization mode

Threats to internal validity

history (external event affects people in an experimental group) -maturation (people adapt/change over time) -attrition (dropping out) -regression to the mean (people don't stay extreme, will score closer to mean when retested)

when external or 'historical' event occurs to EVERYONE in treatment group, *and threat is introduced at same time as treatment* (e.g., "maybe an event happened in the world and that caused the change?"); how to minimize: comparison group helps, but could still occur if event happens only to experimental group.

history threat

Result from a "historical" or external event that affects most members of the treatment groups at the same time as the treatment, making it unclear whether the change in the experimental group is caused by the treatment received or by the historical factor.

history threats

subtraction method: use the differences between means for the conditions (marginal means, e.g., 30 and 0) in a line graph: lines that are not parallel can indicate an interaction in a bar graph: when one set of bars has a greater difference (or displays an opposite pattern) than the other set, this can indicate an interaction is present

identifying interactions

in a table: if there is a large enough difference between column means or row means, you might have a significant main effect. in a graph: for line, sloped or separated lines may indicate a main effect. for bar, differences between bar heights may indicate main effects. *statisitcal test required

identifying main effects

When different groups of participants are placed into different levels of the independent variable

independent-groups design

A design in which both independent variables are studied as independent-groups

independent-groups factorial design

In an experiment of improving children's handwriting, two different techniques of improving handwriting and a control condition are used. Using a pretest/posttest design both groups who received the treatment showed more improvement than the control group. However, the two groups didn't show any difference from each other. The researcher believes that there is a difference, but that the 5-point assessment scale of handwriting cannot detect it. What measurement problem is the researcher concerned with?

insensitive measures

On the first exam in an introductory Psychology class, the grades are lower than Professor Mutola expected. She suspects that multitasking is to blame. She bans computers and cell phones from her class between the first and second exam. When she compares the scores on the two exams, she finds a significant improvement on the second exam. Professor Mutola looks back over the second exam and begins to wonder if it was just an easier exam. What threat to internal validity is she considering?

instrumentation

Occurs when a measuring instrument changes over time.

instrumentation threat

when the 'measuring instrument' (like a survey) changes over time (e.g., therapist changes how he codes the test halfway through study - standards change); how to minimize: - can use posttest only - make sure measures are equivalent - train coders well - counterbalance measures (version A vs. version B at pretest vs. posttest)

instrumentation threat

What is it called when the effect of one independent variable depends on the level of another independent variable?

interaction

What is it called when the effect of one independent variable depends on the level of the other independent variable?

interaction

occurs when the effect of one independent variable differs depending on the level of the second independent variable (can only be detected in factorial/complex experimental designs).

interaction

Whether the effect of the original independent variable depends on the level of another independent variable

interaction effect

in the classical music condition, type of environment had a larger effect than it did in the death metal music condition; the effect of music differs DEPENDING ON the type of environment experienced

interaction example

The most important validity to interrogate when encountering causal claims

internal validity

A quasi-experimental study that measures participants repeatedly on a dependent variable before, during, and after the "interruption" caused by some event

interrupted time-series design

The principle advantage of a within-groups design

it ensures the participants in the two groups will be equivalent

Which of these statements is TRUE of external validity?

it is based on how the sample is obtained rather than sample size

Which of of the following is NOT a problem that may contribute to null effect in a study?

large sample size

A study in which participants are grouped and the participants in each group and combined and studied together

large-N design

The overall effect of one independent variable on the dependent variable, averaging over the levels of the other independent variable.

main effect

overall effect of a single IV on the DV in complex research designs (if experiment has 2 IVs, 2 possible main effects).

main effect

main effect of role, no effect of others present, and an interaction

A variable that is controlled

manipulated variable or independent variable

An extra dependent variable that researchers can insert into an experiment to help them quantify how well an experimental manipulation worked.

manipulation check

A simple average

marginal means

When participants know which group they are in, but the observers do not.

masked design

An experimental design technique in which participants who are similar on some measured variable are grouped into sets

matched groups

A change in behavior that emerges more or less spontaneously over time.

maturation threat

change in behavior that emerges spontaneously over time (e.g., "maybe their depression symptoms just stared to go away on their own?"); how to minimize: inclusion of control group

maturation threat

Some internal validity threats can be addressed simply by including a comparison groups, while other internal validity threats can occur even in studies with a comparison group. Which of the following threats to internal validity would be improved with the inclusion of a comparison group?

maturation threats

mean distance from hole

Marginal Means

means for each level of an independent variable - may or may not be statistically significant (if not- no effect)

These take the form of records of behavior or attitudes, such as self-reports, behavioral observations, or physiological measures

measured variables or dependent variable

Any factor that can inflate or deflate a person's true score on a dependent measure

measurement error

In a study, a way of mathematically averaging the results of all the studies that have tested the same variables, to see what conclusion that whole body of evidence supports

meta-analysis

Which of the following is NOT a form of replication in psychological research?

meta-anaylsis replication

A design in which one independent variable is manipulated as independent groups and the other is manipulated as within-groups

mixed factorial design

An independent variable that changes the relationship between another independent variable and a dependent variable. Results in an interaction

moderator

A study in which researchers stagger their introduction of an intervention across a variety of contexts, times or situations.

multiple-baseline design

After reading a report by Rockoff (2010), Yingying is studying the effects of others present and their roles on the rate of gambling bets using a simulated slot machine. Her levels of others present are one, two, or six. Her levels of roles are gamblers and observers. She constructs a 2 × 3 table of her results of average time between bets. There are two rows for the roles and three columns for the others present. The values in the first row are 15, 15, and 15 and in the second row are 20, 15, and 10. Describe her results.

no effect of role, main effect of others present, and interaction -Increasing the Number of Levels of an Independent Variable—The marginal means differ for both factors and there are differences in the differences in each column.

After reading a report by Rockoff (2010), Yingying is studying the effects of others present and their roles on the rate of gambling bets using a simulated slot machine. Her levels of others present are one, two, or six. Her levels of roles are gamblers and observers. She constructs a 2 × 3 table of her results of average time between bets. There are two rows for the roles and three columns for the others present. The values in the first row are 10, 15, and 20 and in the second row are 20, 15, and 10. Describe her results.

no effect of role, no effect of others present, and an interaction -The marginal means are the same for both factors and there are differences in the differences in each column.

When there is too much unsystematic variability within each group

noise

A quasi-experiemental study that has at least one treatment group and one comparison group, but participants have not been randomly assigned to the two groups

nonequivalent control group design

A study that combines both an interrupted time-series design and a nonequivalent control group pretest/posttest design

nonequivalent control group interrupted time-series design

A study in which participants were not randomly assigned to groups, and were tested both before and after some intervention

nonequivalent control group pretest/posttest design

When the independent variable manipulated by the experimenters did not result in a change in the dependent variable.

null effect

when a study finds that the IV did NOT make a difference in the DV, no covariance (e.g., the treatment "didn't work").

null effect

This occurs when researchers' expectations influence their interpretation of the results

observer bias

occurs when researchers' expectations influence their interpretation of the results; - threatens internal validity and construct validity; solution: double-blind study

observer bias

3. Selection effects

occurs in an experiment when the kinds of participants in one level of the independent variable are systematically different from those in the other. Example: From Chapter 10 : In the autism study, some parents insisted they wanted their children to be in the intensive treatment group rather than the control group. ?Did the researchers use random assignment or matched groups to equalize groups?

Where a researchers recruits one groups of participants, measures them on a pretest, exposes them to a treatment, intervention, or change, and then measures them on a posttest.

one-group, pretest/posttest design

Occurs when exposure to one level of the independent variable influences responses to the next level of the independent variable

order effects

Where only some of the possible condition orders are represented

partial counterbalancng

A variable whose levels are selected (measured) and not manipulated

participant variable

variable whose levels are selected, not manipulated (e.g., gender, age, sex, ethnicity, etc.)

participant variable

Between OR Within? How is a between subjects design different from within subjects design?

participants are only given 1 level of an IV (between) participants are given all levels of an IV (within)

when subjects receiving an experimental treatment experience a change only because they believe they are receiving a valid treatment (e.g., taking a sugar pill)

placebo effects

Dr. Keller wants to test the effect of a new anti-anxiety medication. He recruits a groups of anxious patients and randomly assigns them to two groups. One group will receive his new medication and the other will receive a sugar pill. What is the second group called?

placebo group

When a control group is exposed to an inert treatment

placebo group

Participants are randomly assigned to independent variable groups and are tested on the dependent variable once

posttest-only design

Occurs when a long sequence might lead participants to get better at the task, or to get tired or bored toward the end

practice effects

• Understand the idea of order effects (subtypes: practice effects, and carryover effects), counterbalancing, and the relationship between the two.

practice eﬀects: also known as fatigue effects , in which a long sequence might lead participants to get better at the task, or to get tired or bored toward the end. carryover eﬀects: in which some form of contamination carries over from one condition to the next.

Participants are randomly assigned to at least two groups and are tested on the key dependent variable twice-once before and once after exposure to the independent variable

pretest/posttest design

Experimental Design:What are the pros of such a design?

prioritizes internal validity (correlational research only show covariance; correlations CANNOT show that changes in one variable are only due to the influence of the other variable (this is a failure to rule out 3rd variables)

- allow us to examine EXTERNAL VALIDITY (can add age, ethnicity, gender, etc. to see if results are the same for all groups) - can allow deeper test of theories (most psych theories include more than one variable-allow us to study full theory)

purposes of factorial designs

An experiment in which researchers do not have full experimental control. Participants are assigned to the independent variable by teachers, political regulations, acts of nature-or even by their own choice

quasi-experiment

Used in an experiment to avoid selection effects

random assignment

1. measurement error 2. individual differences 3. situational noise

reasons for within-group variability

Which of the following would not be a cue that the study was a factorial design in a popular press article?

reference to a peer-reviewed journalq

participants may perform very well or very poorly due to chance-if they were tested again then they would 'regress' (go back) to the average score (e.g., HW#3 question with the extreme score during pretest); how to minimize: include control group and closely inspect the data

regression (to the mean) threat

A statistical concept called regression to the mean: When a performance is extreme at Time 1, the next time that performance is measured (Time 2), it is likely to be less extreme-that is, closer to a typical or average performance.

regression threat

A type of within-groups design in which participants are measured on a dependent variable more than once-that is, after exposure to each level of the independent variable

repeated-measures design

Pertaining to a study whose results have been obtained again when the study was repeated

replicable

A study in which researchers replicate their ordinal study but add variables to test additional questions

replication-plus-extension

multiple-baseline design :

researchers stagger their introduc-tion of an intervention across a variety of contexts, times, or situations.

A study in which a researcher observes a problem behavior both with and without treatment, but takes the treatment away for a while to see whether the problem behavior returns

reversal design

In a business class experiment on the endowment effect, Theo is comparing the value of a coffee mug to someone who owns it and is selling it to someone who is buying it. The endowment effect describes the tendency of sellers to value something they own more than buyers do. Participants are randomly assigned to be buyers or sellers of a mug with their first name on it. Buyers select the maximum price they would pay for the mug. Sellers select the minimum price they would accept for the mug. What is the independent variable in this experiment?

role of the participant

A study in which researchers gather information from only one animal or one person

single-N design

External distractions of any kind-a third factor that could cause variability within groups and obscure true group differences

situation noise

Occurs in an experiment when the kinds of participants in one level of the independent variable are systematically different from those in the other. These occur when the experimenters let participants choose which group they want to be in. Also, when experimenters assign one type of person to one condition, and another type of person to another condition.

selection effect

Participants in a research study are given a list of words to study for 3 minutes and then, following a delay are asked to recall the list. The length of the delay is manipulated between participants to be either 2 minutes, 5 minutes, or 10 minutes. Since the different groups need different amounts of time, the first 25 participants who arrive are assigned to the 10-minute group, the next 25 are assigned to the 5-minute group, and the final 25 are assigned to the 2-minute group. What confound does this create?

selection effect

An outside event or factor systematically affects people in the study-but only those at one level of the independent variable

selection-history threat

irrelevant events, sounds, or distractions in the external situation that create unsystematic variability within groups in an experiment.

situational noise

A study in which researchers gather information from just a few cases

small-N design

• Experiments

speciﬁcally means that the researchers manipulated at least one variable and measured another

A study in which a researcher observes behavior for an extended baseline period before beginning a treatment or other intervention; if behavior during the baseline is stable, the researcher is more certain of the treatment's effectiveness

stable-baseline design

• Understand what random assignment is supposed to do and why we use it. Understand the relationship between internal validity and random assignment. (Not to be confused with random selection)

supposed to do:ensures that every participant in an experiment has an equal chance to be in each group. why we use it: it's a way of desystematizing the types of participants who end up in each level of the independent variable.

tastiness and expensiveness

The process of using a factorial design to test limits

testing for moderators

A specific kind of order effect, refers to a change in the participants as a result of taking a test (dependent measure) more than once. People may have become more practiced at taking the test, leading to improved scores, or they may become fatigued or bored, which could lead to worse scores over time.

testing threat

scores have changed over time just because subjects have taken the test more than once, meaning the participant changes (e.g., "maybe subjects have adapted to the test after taking it the first time?"); how to minimize: - use comparison group - drop pretest (use post-test only) - use alternative form of pretest; occurs in a repeated-measures experiment or quasi-experiment

testing threat

Interaction cont.

the difference of the simple differences -interaction is almost always more important

In a factorial experiment, which is the most important effect?

the interaction

Main Effect

the overall effect of one independent variable on the dependent variable, averaging over the other levels of he other independent variable - not necessarily most important -simple difference

The are that encompasses the extreme 5% of a distribution is frequently referred to as

the rejection region

What does a moderator effect say about external validity?

the relationship you found does NOT generalize to ALL people in the population the relationship is stronger/weaker for certain groups of people

A researcher's intent for a study, testing association claims or causal claims to investigate support for a theory

theory-testing mode

When researchers use a small- N design , instead of gathering a little informa-tion from a larger sample:

they obtain a lot of information from just a few cases. They may even restrict their study to only one animal or one person, using a single- N design . Large -N designs and small -N designs differ in two key ways, sum-marized in

In a 2 x 2 x 2 factorial design, what are all the possible effects to test?

three main effects, three two-way interactions, and a three-way interaction

What are the two main reasons to use factorial designs?

to test limits and to test theories

What are the two main reasons researchers use factorial designs?

to test the limits of an effect and to test theories

Susan ran a study in which she had a group of younger adults (18-24 year-olds) and older adults (50-60 year-olds). She had both groups recite a poem by memory once in front of an audience of 50 people and once in a room by themselves. She counterbalanced the order of these tasks between participants. She had the participants rate their level of anxiety right before they recited the poem each time. Susan found that there was a main effect for age such that younger people reported being more anxious than older people. She found a main effect for audience size such that people were more anxious in the room with 50 people than they were in the room by themselves. She did not find an interaction in the results. If Susan were to graph her results, what would they look like?

two parallel diagonal lines

type of commercial shown

moderator

variable that changes the relationship between two other variable. -in factorial language moderator is an independent variable that changes the relationship between another independent variable and a dependent variable. (results in an interaction) i.e. driver age did not moderate impact of cell phone use on brake time

An experiment in which all the participants plan to receive treatment, but are assigned to do so at different times

wait-list design

observer bias, demand characterizations, and placebo effects

what are the 3 threats that apply to any experiment?

maturation threats, history threats, regression threats, attrition threats, testing threats, and instrumentation threats

what are the 6 common threats to internal validity?

does single IV have significant effect on DV?

what do we ask in "simple" experimental designs?

does each IV have significant effect on DV?

what do we ask in factorial experimental designs?

too much variability (noise) within the groups - 'error variance'; difference between groups is the same, but higher variability within - more overlap (smaller effect size and less likely to be significant)

what ways does it obscure between-group differences?

cross over interaction

when lines cross each other in demonstrating interaction (hot and cold foods/ ice cream pancakes)

interaction, because it's the full story; "X" makes a difference but especially at "Y"

when main effects and interactions are both present, which should you focus on?

What is an interaction effect?

with a factorial design we can formally test "it depends" the effect of one IV depends on the other IV you have an effect only under certain conditions (or for certain people) a difference in differences

A design in which there is one group of participants and they all participate in all combinations, or cells of a design

within-group factorial design

variability within the groups?

within-group variance

within-groups

When there is only one group of participants, and each person is presented with all levels of the independent variable

EXP PSYCH FINAL 8,9,10,11 TERMS & QUESTIONS & CONCEPTS

Set pelajaran terkait

Chapter 3 Culture

Chapter 5, 8 & 10

Psyc362 Midterm

Macro Exam 1 (Chapter 6-11)

Cost Accounting Chapter 6

CARCINOGENESIS

Forensic Semester Test

Chapters: 14, 15, 17

INR 2002 Final

CIST 2411 Final Exam

HESI Missed Questions

Art Appreciation 4.7-4.9

Ch 31 - Serious Mental Illness

*Chapter 40: Care of Patients with Hematologic Problems

Chapter 9

SMM Midterm Study Guide S23

Ch. 23- Prep for Exam

chapter 22 - investments

Economics -- Chp 7 (pg. 88-91)

PrepU Ch19 Drug Therapy With Aminoglycosides and Floroquinolones