PSYCH 302 Research Methods
The only control technique that can account for both known and unknown sources of extraneous variation is
c. random assignment.
When one of the matching techniques is used,
c. randomizing should still be used where possible.
Participants in human experiments are generally selected
**a. based on convenience and availability.
A researcher predicts that tennis professionals will play better in front of an audience. Less capable tennis players, however, are expected to do better without an audience. The researcherSelect one
**a. expects an interaction effect to occur. x b. is predicting a main effect for the audience variable. x c. is using a mixed design. x d. is predicting a main effect for ability of the tennis player.
The most basic and simplest matching technique is to
**a. hold the extraneous variable constant
Two classes of students at different schools are closely matched on IQ scores. One class is being taught with the standard method and the other class is being taught with a new technique. The two classes are then to be compared on scores from a standardized test at the end of the year.
*c. even though matched on IQ scores, the classes may not be equivalent on many other variables
Rhonda designs an experiment in which half of her participants are randomly assigned to view a sad movie and half view a comedy, but all participants fill out three mood surveys at one, two, and three weeks after the movie. This is an example of
*d. a mixed-model, factorial design.
In a between-participants posttest-only design
*d. each participant is tested in only one treatment condition
Which of the following should be done first during debriefing?
*d. let participants ask questions about their experience
Perhaps the greatest technological advance in experimental apparatus has beenSelect one:
*d. the arrival of affordable, easily programmed microcomputers.
The most common criticism regarding the use of college student participant pools is that
.**b. it may compromise external validity
The primary concern of the Institutional Review Board (IRB) is to
.**c. protect the welfare of human participants.
Researchers would like for power to be at least
.80
The director of marketing for a local company mails out 10,000 surveys in her city to evaluate the appeal of her company's new products. Based on what she learned in her college research methods course, she can expect a return rate of after the initial mailing
20-30%
An experiment was designed to determine if gender of the interviewer and the amount of eye contact by the interviewer will influence the participant's liking of an interviewer. Thus participants were randomly assigned to groups that had either a male or female interviewer who made little, moderate, or sustained eye contact. At the end of the sessions, the participants were asked to rate their liking of the interviewer. This is a __________ design.
2X3 factorial
In survey research ___________ is more important than in experimental research and so ________ sampling is more likely to be utilized.
generalizability; random
In most cases there is a ___________ relationship between internal and external validity.
inverse
Effect size is the
magnitude of the relationship between the independent variable and the dependent variable.
An urban community clinic wants to try a new method of getting drug addicts to kick their addiction. They advertise for participants in their lobby, and start the first 20 volunteers on the program. Three months later, they find that 65% of the volunteers are off drugs. This example illustrates the possibility of ________________ as a plausible rival hypothesis.
selection
The primary threat to internal validity in the nonequivalent comparison group design is some form of a ______________________ effect.
selection
Which of the following threats to internal validity is most likely to be a problem in the nonequivalent comparison group design?
selection bias
Dr. Beckweth is interested in the effects of tutoring on success in calculus. She also knows that gender is an important issue in math success, so she factors that in as a second independent variable. She studies calculus success in the following four groups of participants: males who have received tutoring, females who have received tutoring, males who have not received tutoring, and females who have not received tutoring. What statistical test should she use to examine her results
two-way analysis of variance
Suppose you have created a new method of diagnosing anxiety disorders. How could you demonstrate that your method is a construct valid?
use your method to diagnose a group of participants, then see if your diagnoses match with diagnoses taken from other, established methods
The quality of an experiment is judged by its internal validity. When we say that an experiment is internally valid, it means that
we can confidently state that any observed changes in the dependent variable result from manipulations of the independent variable(s) and nothing else.
What is the major advantage of a within-participants design?Select one:
x a. the data are easier to interpret than are data from between-participants designs x b. it does not carry the risk of carryover or sequencing effects **c. the experimenter doesn't have to worry about whether the groups of participants are equivalent to each other x d. it is not subject to the influence of expectancy effects
The defining characteristic of a factorial experimental design isSelect one:
x a. the measurement of more than one dependent variable. x b. the manipulation of one independent variable. **c. the manipulation of more than one independent variable. x d. inclusion of more than two cells.
A major advantage of randomly selecting participants from a population is that
you can be more confident that your sample is representative of the population.
According to research by Kimmel (1991), IRB decisions seem to be partially dependent on .
**c. gender (male reviewers are more likely to approve studies).
Which of the following is NOT true with regard to procedures?
as long as the instructions are uniformly presented, it is not very important how an experimenter greets and otherwise interacts with the participants
The purpose of random ______________________ is to produce a set of groups that are similar on all possible factors at the beginning of an experiment.
assignment
If an IRB refuses to approve a study the researcher
must abide by their ruling and either redesign the study or not conduct it.
Two teachers who are friends teach math at different high schools. At a conference, they learn about a new program for teaching trigonometry. They decide to test it by having one teacher use it in her class and the other use the traditional program, then compare their students' scores on the AP trigonometry test. This is an example of which experimental design?
non-equivalent posttest-only design
Danielle conducted a study on cartoon watching and children's attention. She showed one group an educational cartoon and one group a non-educational cartoon. The group that saw the educational cartoon showed higher levels of performance on the attention test. Danielle decided to reject the null hypothesis. Really, what she is doing is saying that the difference between groups is
not due to chance
Which of the following is a clear example of an interaction?
rats given a drug in the morning are more active than rats given placebo and rats given placebo in the evening are more active than rats given drug.
The presence of a crossover effect in one's data can usually rule out the influence of which rival hypothesis?
regression-artifact
The two most important techniques for eliminating potential rival hypotheses are
random assignment of participants and use of control groups.
Because researchers are generally more concerned with establishing internal validity rather than external validity, they are typically more concerned with _________ and less concerned with ____________.
random assignment; random selection
Often, we do not know at the start of an experiment what extraneous variables could affect our results. The best means of controlling unknown sources of extraneous variables is
randomization
What is reliability?
the consistency with which the same event is repeatedly measured. scores are consistent across repeated testing.
Which of the following is NOT one of the requirements of the regression-discontinuity design.
the cutoff score should be located at one of the extreme ends of the distribution
What is validity?
the degree to which a test measures what it says it measures. the peabody test said it measured intelligence. however, it only tests receptive vocabulary, so that's not valid.
Discriminant validity refers to
the degree to which the measure does not correlate with measures of different constructs.
Dr. Sheffield wants to investigate the causal relationship between frustration and memory. She divides participants into two groups using random assignment. One group is given a problem to solve that has no solution, inducing frustration, while the other group is given a problem to solve that has a solution. Then both groups have their memory tested. The group that is in the frustration condition can also be called the
**a. experimental group
The nonequivalent posttest-only design differs from the one-group posttest-only design and the one-group pretest-posttest design in that
**a. it has a comparison group.
The major disadvantage of a within-participants design is that Select one: a. it is very susceptible to order and carryover effects. b. it is difficult to interpret the data it produces. c. it does not guarantee equivalence across groups of participants d. it is unusually vulnerable to influence of expectancy effects.
**a. it is very susceptible to order and carryover effects.
A mixed factorial design has
**c. at least one between-subjects factor and at least one within-subjects factor.
A group of physicians tests a new analgesic on their patients with chronic pain problems. They obtain patient ratings of pain, administer the new drug for a week, and then obtain pain ratings again. They find that pain ratings are down 10 points at their second observation. This is an example of which experimental design. Select one:
**a. one-group pretest-posttest design x b. non-equivalent posttest-only design x c. one-group posttest-only design x d. non-equivalent before-after (pretest-posttest) design
Dr. French makes sure that she has multiple video cameras recording her observation room during data collection. She also has multiple research assistants review the video recordings after the data are collected. This is to control for
**a. recording errors
In the one-group pretest-posttest design which of the following threats to internal validity is NOT controlled?
**a. testing
Factorial designs are very frequently used because they have many advantages. Which of the following is NOT among them?Select one:
**a. the results are easy to interpret x b. more than one hypothesis can be tested x c. potentially confounding extraneous variables can be incorporated into the experiment d. possible interactions among independent variables can be explored
When conducting an Internet based study it is a good idea to not only conduct a pilot study using several participants but to also complete the study yourself becauseSelect one:
**a. this will allow you to determine if the data collected will be returned to you is an manner that is understandable and arranged in a way that can be statistically analyzed.
Which of the following is NOT the purpose of creating the research design for a research problem?
**a. to analyze the data collected
In a 4x2 factorial design, there are
**a. two independent variables with 4 levels on one and 2 levels on the other
In a 4x2 factorial design, there are independent variables.Select one:
**b. 2
The posttest-only control group design requires Select one:
**b. a control condition. xc. matching on at least one extraneous variable. x d. random selection of participants.
Postexperimental interviews fulfill many obligations the experimenter has toward his or her participants. Which of the following is NOT among them?
**b. assessing whether the participant would like to be trained as a researcher, too
One way in which experimenter expectancy effects can be manifested is in errors in recording data. What is the best way to control this? Select one:
**b. automate the data collection as much as possible
Psychology participant pools provide a ________ sample.
**b. convenient
Postexperimental interviews are particularly important when, experimental procedures involves the use of
**b. deception
It is usually impossible to eliminate the effects of extraneous variables. However, it may be possible to eliminate
**b. differential effects of extraneous variables.
In all repeated-measures designs
**b. every participant will be tested in each of the conditions of the study.
Which of the following is NOT an advantage that comes from automating one's experimental apparatus?
**b. increased power of statistical testsx
Which of the following is NOT a disadvantage of the individual matching?:
**b. it is often difficult to arrange for two participants to arrive at the experimental site at the same time.
Random assignment of participants to the various groups in an experiment Select one:
**b. maximized the probability that extraneous variables will NOT have a differential effect on the various treatment groups.
The major advantage of individual matching is that
**b. one can be sure that the two groups of participants are equal on the matched extraneous variables.
Evelyn has a new speed reading program she wants to test. She trains 6 people on her program, then measures their reading speed. This is an example of which experimental design?
**b. one-group posttest-only designx
Frequently, experimenters try out new procedures and/or apparatuses by running the experiment using just a few participants. This experiment is called a
**b. pilot study
What is the factor that makes the between-participants posttest-only design
**b. random assignment helps insure that the two experimental groups are essentially Equivalent at the outset
Which of the following is the proper sequence of steps in conducting an experiment with individual matching? Select one:
**b. select a sample of research participants, match each participant with another person one the selected matching variable(s), randomly assign each member of the matched partners to each group, administer the treatments to the groups, measure the dependent variable(s)
As sample size increases
**b. the ability to detect statistically significant differences among groups.
What is the primary benefit of matching?
**b. the influence of the variables on which participants are matched is spread evenly across groups
In a 2 (age) x 2 (type of therapy) factorial design, which of the following outcomes would be an example of an interaction?
**b. therapy A works better for young adults, while therapy B works better for older adults
What is the common purpose of using the double blinding and deception techniques?Select one: a. they eliminate experimenter bias
**b. they keep participants' perceptions of the experiment constant across different conditions of the experiment
Which of the following is NOT typically considered to be a function of debriefing?
**b. to obtain demographic information from the participantsx
When would an experimenter want to use "yoked" matching of participants?
**b. when the temporal sequence of experimental events could be confounded with the independent variable and influence the results
The "sensitivity" of an experiment refers to its ability to detect any differences in performance, however small, between the two groups. In one technique to improve sensitivity the experimenter uses matching of participants across groups, assuring that
**c. groups of participants are equated on those selected extraneous matching variables.
The most important difference between weak and strong research designs is that strong designs .
**c. have greater internal validity.
Jennifer wants to study motor-pursuit performance (tracking a moving light with a hand-held wand) under each of three conditions of distraction, high, medium, and low. Instead of using three separate groups of participants, she makes sure her groups are equivalent by testing the same 12 participants under all three conditions of distraction. She finds that performance is poorest in the first (high distraction) condition, better in the second (medium distraction), but best in the third (low distraction) condition. She concludes that performance is hindered by distraction. What is the problem with this interpretation?
**c. her participants could have improved simply with practice over the three conditions
Reporting of details regarding participant characteristics, selection, and assignment procedures
**c. is important to enable other researchers to replicate your findings.
Which of the following is NOT an advantage of a within-participants design?
**c. it is relatively immune to carryover effects
What is the purpose of "blinding" the experimenter to the condition(s) his or her participants are experiencing?
**c. knowing this information may cause the experimenter to behave differently toward participants in the different conditions
If you are interested in any possible interaction effects between an extraneous variable and the independent variable, which of the following techniques you should use?
**c. matching by making the extraneous variable into another independent variable
Suppose you are conducting a factorial study with variables A and B. Your results reveal an interaction effect. This means that
**c. the effect of independent variable A depends on what level of independent variable B they experience.
Generally speaking, as the number of the participants in the study increases,
**c. the likelihood of making a Type II error also increases.x
One problem, noted in your text, with recruiting research participants through the Internet is that
**c. the participants may not be representative of non-Internet users
Suppose you are interested in studying how prior exposure can affect color preference, but you know that color preferences are also a function of ethnic background. You could increase your study's sensitivity by studying only one ethnic group. There is a problem inherent in this approach, which is that
**c. your results would not be generalizable beyond the ethnic group you studied.
How many possible sequences would be needed for complete counterbalancing with three treatment conditions?Select one:
**d. 6
What is the advantage of a double-blind experimental design? Select one: and eliminates the possibility that the experimenter unintentionally signals the expected outcome to the participants.
**d. It makes the demand characteristics the same for participants in all conditions and eliminates the possibility that the experimenter unintentionally signals the expected outcome to the participants.
When choosing between a within-participants design and a between-participants design, one is often considering a tradeoff between?
**d. a more sensitive design with the former and a more controlled design with the latter.
A power analysis allows you to determine the number of participants needed if you also know
**d. alpha, power, and effect size.
Pilot" research allows the investigator to
**d. check out the procedures before collecting the real data.
What is the best technique to use to control for sequencing effects? Select one:
**d. counterbalancing
By using intragroup incomplete counterbalancing, you can control for all of the following EXCEPT Select one:
**d. differential carryover effects
If human participants cannot be selected randomly,
**d. it becomes more important to report exactly how participants were selected and assigned.
Which of the following is NOT a benefit of incorporating a pretest into your experimental design?
**d. it can sensitize the participants to the experimental treatment
A research study examined the effects of playing violent or non-violent video games on the aggressive behavior of children of two different ages (10 year olds and 13 year olds). The researchers found that, regardless of age, children who played violent video games were more aggressive than those who played non-violent video games. This finding represents a
**d. main effect.
In the context of experimental design, "double blind" refers to the situation in which
**d. neither the experimenter nor the participant knows which experimental treatment the participant is receiving.
Which of the following extraneous variables can NOT be corrected using random assignment? Select one:
**d. participant and experimenter effects
In within-participants experimental designs, participants are tested under more than one condition. A carryover effect may confound the results if Select one:
**d. performance under the later conditions is altered by participating in the prior conditions.
What should be the main determinant of what kind of organism is used in a given experiment?
**d. precedent; what others in the field use
Because researchers are generally more concerned with establishing internal validity rather than external validity, they are typically more concerned with _________ and less concerned with ____________.Select one:
**d. random assignment; random selection
Dr. James is conducting a repeated measures study in which the IV has three levels. Dr. James randomly assigns one of the six possible sequences of levels to each participant. This type of counterbalancing is called Select one:
**d. randomized counterbalancing
Carryover effects occur when
**d. something internal to the participants changes over time that is unrelated to the independent variable.
Which of the functions of debriefing is probably least likely to be accomplished?
**d. the educational value function
The major fault in the one-group pretest-posttest design is that
**d. there is no way to examine the effects of history and maturation on the results.
Factorial designs present many problems. Which of the following is NOT among them?
**d. they can be used with one or more factors or independent variables
Dr. Bassuk is conducting a pilot study for his newest research project. During this pilot study, he has the participants verbalize their thoughts as they perform the experiment. This technique is called the
**d. think-aloud technique
Although the extent to which experimenter effects influence study outcomes is controversial, techniques have been developed to at least partially counteract these effects. Which of the following is the LEAST likely to be used?
**d. using a random sample of experimenters to control for experimenter attribute effects
The difference between a factorial experimental design and a one-way design is that
*a. a stronger case for causality can be made with a factorial design.x
According to your text what is the primary disadvantage of posting debriefing information on a website?
*a. an inability to assess the psychological state of the participant
Any experimental design that incorporates more than one independent variable is called a _______ design.
*a. factorial
The consent to participate statement must include all of the following, except which one?
*a. funding sources and any governmental agencies affiliated with the study.
Why does a good experiment include a control group?
*a. it gives us information about how participants would perform without experiencing the experimental treatmentx
The pretest-posttest control group design is also considered a _________ design.
*a. mixed
Power refers to
*a. the chances of rejecting the false null hypothesis.
What is the important difference between the between-participants posttest-only design and the flawed non-equivalent posttest-only design?
*a. the former uses random assignment of participants to groupsx
Power of a statistical test refers to
*a. the probability of rejecting a false null hypothesis.
The Institutional Animal Care and Use Committee (IACUC) judges which of the following?
*a. whether methods of euthanasia are in accordance with accepted procedures
________ occurs in a factorial design when there are differences on the dependent variable in the different levels of one condition, that are consistent across the levels of the other independent variable.
*b. main effectx
A research design that contains both between participants and within participants variables is called a
*b. mixed designx
The two most important techniques for eliminating potential rival hypotheses are
*b. random assignment of participants and use of control groups.
Suppose you have gone to great lengths to determine which participants will perform the experiment at what time and in what group, but some participants just fail to show up for their appointments. What should you do?
*b. randomly select and assign new participants to take their place
The major fault in the non-equivalent posttest only design is that
*b. the two groups are may not be equivalent at the beginning.x
When selecting participants from a population, experimenters need
*b. to be concerned about differences between volunteers and nonvolunteers.
The session that the researcher holds with participants at the conclusion of the experiment is called
*c. a postexperimental interview.
Which of the following is an advantage of within-participant designs over between participant designs?
*c. a reduction in the number of research participants needed
How might you solicit individuals for a study via the Internet?
*c. all of the above are potential ways of soliciting participants
How many possible sequences would be needed for complete counterbalancing with three treatment conditions?
6
The outcome from a nonequivalent comparison group design that gives us the most confidence that the treatment produced the observed effect is
A crossover effect
Hypothesis testing is
A) one method of making inferences about populations based on samples. B) a method that tests only the null hypothesis. C) a method of determining support for the scientific hypothesis by rejecting the null hypothesis. D) all of the above.
If I have studied the effect that three dosages—15, 30, and 60 mg—of the drug Cymbalta has on depressed people and people with an eating disorder and have found that the lower dosages are most effective with people with eating disorders and the higher dosages are most effective with people with depression, I have identified
An interaction between the drug dosage and the type of disorder
Scales of measurement and examples
Nominal named variables Ordinal named+ ordered variables Interval named +proportionate intervals between variables Ratio named+oredered+proportionate intervals between variables+ can accommodate absolute zero
Most of the threats to internal validity are ruled out in the interrupted time-series design As a result of a discontinuity in the one-point immediately before and the one point immediately after the treatment
As a result of the multiple pretests and posttests
Which is the correct order of the scales of measurement?
Nominal, ordinal, interval, ratio
If you wanted to control for the expectancies that the experimenter might have regarding the outcome of the experiment, you might
Automate the experimental procedure so that the experimenter does not interact with the research participant
Which of the following journals will be helpful in identifying a specific piece of apparatus or computer program to assist in data collection? Journal of Applied Psychology Psychological Methods Psychological Assessment
Behavioral Research Methods, Instruments, and Computers
If you have pretested your entire procedure on a few participants prior to actually collecting data, you have
Conducted a pilot study
Assume you wanted to find out if alcohol increased a person's aggressiveness. To test this hypothesis, you wanted to test people's aggressiveness while they were under the influence of alcohol and while they were not. However, you know that you are asking people to perform under two conditions and that performing once might change their performance on the second occasion. To control for this effect, you elect to
Counterbalance the administration of the alcohol and no-alcohol condition
Dr. Know conducted an experiment on youth violence and found that his treatment was effective when he conducted it at the Strickland Youth Center; so, he also tried it at the Boys Club, testing which threat to external validity?
Ecological validity threat
What function does debriefing serve?
Ethical function educational function Methodological function Participant satisfaction from contributing to science All of the above are functions of debriefing
If I have conducted an experiment that requires me to randomly assign 30 participants to two levels of one independent variable (15 in one condition and 15 in the other condition) and all 30 participants take all three levels of a second independent variable, I have used what type of design?
Factorial design based on a mixed model
If an experiment had four conditions (A, B, C, and D) and each participant is to be measured under each condition, intragroup incomplete counterbalancing might be the best method to use. Which of the following describes this method?
Group I: ABDC; Group II: BCAD; Group III: CDBA; Group IV: DACB
Dr. Prediction conducted an experiment investigating future predictions of violent behavior and found that children who hurt animals are more likely to become spouse abusers. From the results of this study, he wrote a book that had as its thesis the fact that parents should use children's behavior toward pets as an indication of their future behavior toward others, and if they see them consistently abuse pets, they should get their children some help. In suggesting that his experiment applies to other children, Dr. Prediction assumes that his study
Has external validity
What is the advantage of a double-blind experimental design?
It makes the demand characteristics the same for participants in all conditions and eliminates the possibility that the experimenter unintentionally signals the expected outcome to the participants.
Assume that you wanted to investigate the effect of caffeine on a person's ability to identify the number of times the letter q appeared in a page filled with a random list of letters. To control for the effect of a person's reaction time, you divided people into those that had high and low reaction times and then included this difference in reaction time as another independent variable in the design of your study. By controlling for the possible influence of reaction time in this way you used
Matching by including the extraneous variable into the design of the study
If you identify extraneous variables that are correlated with the dependent variable and control for them by matching participants on an individual basis and then randomly assign the matched participants to groups, which control technique have you used?
Matching with random assignment
__________________________ is the process of assigning symbols or numbers to objects, events, people, or characteristics according to a specific set of rules.
Measurement
Aaron is arguing with Miriam about experimental design. Aaron says, "The nonequivalent posttest-only design is a true experimental design because it uses random assignment!" Miriam responds, "No--you've got that wrong. You must mean the between-participants posttest-only design." Which one of them is correct?
Miriam only
If you could use only one control technique, which one should you use?
Random assignment of participants to groups
________________ of participants is done to obtain a representative sample, and __________ of the participants is done to improve the experimental design of the study.
Random selection; random assignment
What differentiates interval from ratio scales of measurement?
Ratio scales include an absolute zero point - indicating the absence of what is being measured
A school superintendent wants to decrease the amount of truancy that exists in her school system. She assigns all those students who have missed coming to school an average of twice every week for the past year to participate in a program designed to make school more enjoyable and rewarding. The students with an average of less than twice a week will serve as controls. To test the effectiveness of this program she would probably use which design?
Regression discontinuity design
______________ refers to the consistency of results and ____________ is the extent to which you are measuring what you think you are measuring.
Reliability; validity
If a research study permits you to accurately infer that the independent variable is the cause of the changes observed in the dependent variable, then you have a study
That has internal validity
John Brown has signed up for a social psychology study. His friend just completed the study and told him that he experienced smoke coming into the room while they were completing some questionnaires. His friend told him that he thought the study was investigating a reaction to the smoke and not the response to the questionnaires. When John arrived at the experimental site and heard the experimenter's instructions, he evaluated the things he was told to see if the experiment was about the reaction to smoke. John's behavior
Represents an example of demand characteristics
In a 4X2 factorial design there are _________ cells.
Select one :x a. 2 **b. 8 x c. 6 xd. 4
There are many good reasons for pretesting participants before introducing the independent variable. Perhaps the most common of these is that pretesting
Select one: x a. is a prerequisite for posttesting. **b. gives the experimenter direct evidence of change in performance. x c. eliminates the need for random assignment of participants to groups. x d. increases the sensitivity of the experiment
The type of organism that should be used in research studies
Should be determined by the research question
1. Which of the following sampling techniques is an equal probability selection method (i.e., EPSEM) in which every individual in the population has an equal chance of being selected?
Simple random sampling Proportional stratified sampling Cluster sampling when the clusters are of equal size All of the above are EPSEM
Sometimes experimental methods to control for extraneous variables cannot be implemented or are not completely effective. For example, ethical considerations may prevent random assignment. In these instances, that research may rely on what method:
Statistical Control
If a research study revealed that the independent and dependent variables covary in the study sample, and they really do covary in the population, the study has been demonstrated to be worthwhile
Statistical conclusion validity
When we talk about the validity of psychological research studies we are referring to:
Statistical conclusion validity Internal validity Construct validity External validity All of the above
Determining the sample interval (represented by k), randomly selecting a number between 1 and k, and then including every kth element in your sample are the steps for which type of sampling?
Systematic sampling
Types of reliability
Test-retest - The same test over time. Inter-rater - The same test conducted by different people. Parallel forms - Different versions of a test which are designed to be equivalent. Internal consistency - individual items of a test.
Reliability of a test refers to which of the following?
The consistency or stability of test scores
The one-group posttest-only design, the one-group pretest-posttest design, and the posttest-only design with nonequivalent groups have in common
The fact that they do not control for threats to internal validity
The power of a statistical test is determined by
a. all of the above
Types of Validity
The internal -extent to which we can draw cause-and-effect inferences from a study The external - extent to which we can generalize findings to real-world settings Construct - the extent to which variables measure what they are supposed to measure Statistical - the extent to which statistical conclusions derived from a study are accurate and reasonable Face - the extent to which respondents can tell what the items are measuring
A control group is needed
To control for some rival hypotheses To serve as a comparison (Both a and b are correct)
Dr. Mai conducts a test of a new anti-malaria drug in Africa and concludes that he may reject the null hypothesis with a probability level of 0.04. He concludes, therefore, that his drug works. In reality, however, it does not. Dr. Mai has committed a error.
Type I
The primary difference between a between-participants and a within-participants design is The number of independent variables they can test
Whether the various treatment combinations use different participants or the same participants
Human participants must sign a "consent to participate" form (unless exempted) prior to being in the experiment. This form should include all of the following EXCEPT
a disclaimer saying that the experimenter is not responsible for any harm to the participant.
A "participant pool" is
a group of potential research participants (usually college students).
Each year the graduating class at Stoner High is given a survey to assess their drug use. The same survey has been used for 10 years allowing school administrators to track changes in drug use over time. This method of survey collection is referred to as
a trend study
Two middle school teachers want to find which of three new violence prevention programs would be most effective in their school. From September through November, program #1 is in effect. It is then replaced by program #2 from December through February, and then program #3 runs from March through May. In June the teachers examined fight reports for the school year and find that there were 14 fights in the fall, 10 fights in the winter, and 6 fights in the spring. They conclude that program #3 is most effective is stopping violence. Which of the following is a plausible rival hypothesis to their interpretation? Select one:
a. fighting decreases in spring, anyway b. the effects of programs #1 and #2 could have carried over into the spring c. whatever program came third might have been associated with the fewest fights d. all of the above are plausible alternative explanations
Dr. Bassuk is conducting a pilot study for his newest research project. During this pilot study, he repeatedly stops the participants and interviews them. He asks them to report what they were thinking during each portion of the study. This group of participants in the pilot study can also be called a
a. sacrifice group
Which of the following factors should you consider when deciding on what research design to use?
a. use of a pretest b. use of a control group c. number of groups *d. all of the above
Even though psychologists are interested in behavioral diversity, most participants in psychological experiments are
animals and introductory psychology students
The omission of or alteration of the truth of information give to participants in a research study can be done to
b. control for participant effects
In individual matching, Select one
b. each participant in one group is equated with another participant in another group on selected extraneous variables (e.g., education level).
Suppose a researcher were reporting on a factorial experiment in which she simultaneously manipulated two independent variables. One of the independent variables was presented between participants and the other was presented within participants. This is an example of a design.
b. mixed model
Which of the control techniques has the most power to insure that unidentified, extraneous variables do not have differential effects on the different groups in the experiment?
b. randomization
An experiment was designed to determine if gender of the interviewer and the amount of eye contact by the interviewer will influence the participant's liking of an interviewer. Thus participants were randomly assigned to groups that had either a male or female interviewer who made little, moderate, or sustained eye contact. At the end of the sessions, the participants were asked to rate their liking of the interviewer. This is a __________ design.
between-participants
In a study designed to examine the effects of caffeine on reaction time, four caffeine conditions (100, 200, 300, and 400 mg of caffeine) are used. If the experimenter decides to use complete counterbalancing and assuming that one subject will be tested in each of the sequences used, how many people will be needed to complete the study?
c. 24
If an experiment had four conditions (A, B, C, and D) and each participant is to be measured under each condition, intragroup incomplete counterbalancing might be the best method to use. Which of the following describes this method? Select one:
c. Group I: ABDC; Group II: BCAD; Group III: CDBA; Group IV: DACB
Which of the following is not a typical source of order effects?
c. aging
If a researcher is worried about experimenter bias during the interaction between experimenter and participant, _________ could totally control for this bias by removing the experimenter from interaction with the participant completely.
c. automation
Participants in a memory experiment are asked to learn a list of high-imagery words and then to learn a list of low-imagery words. Using the same participants in each condition could cause it to be confounded by
c. carryover and/or order effects.
___________ must be used with repeated measures designs.
c. counterbalancing
In what counterbalancing technique would you present experimental treatments to participants in one order, and then in the reverse order? Select one:
c. intrasubject counterbalancing
The main disadvantage of intrasubject counterbalancing is
c. it requires many test conditions for each participant and thus can take a long time.
If it is not feasible to use a blind technique throughout the whole experiment, the alternative is the
c. partial blind technique.
Hannah wants to see if her new technique of ping-pong playing can increase one's ping-pong performance. She asks the U.S. Olympic ping-pong team to work with her. Half of the U.S Olympic team is randomly assigned to be taught by the new style, the experimental group, and the other randomly assigned half are not, the control group. Her technique does not significantly increase the performance of the experimental group compared to the control group, perhaps because they are already so good at the sport. This could be an example of
ceiling effect
Gerald is developing a measure of shyness and he determines that students scoring high on the measure also score high for introversion on a well known introversion extraversion scale. The outcome best illustrates
concurrent validity.
A good way to work out the kinks of an experiment is to
conduct a pilot study
In some experiments, demand characteristics are controlled by making sure neither the participant nor the experimenter knows what condition(s) the participant experienced until the data are collected and analyzed. This is called a----- procedure. Select one: a. matched ignorance b. counterbalancing c. treatment-placebo d. double-blind
d. double-blind
A study examines scores on an employment test and job performance six months later. This study is most likely attempting to establish
criterion validity.
Sometimes, the treatment received in one condition of an experiment can influence behavior under the next condition. This is known as a ___ effect.
d. carryover
Participants volunteered to be in a study of the effects of vitamin supplements. The experimenter was given an unlabeled syringe containing saline or a vitamin supplement to inject into the participant. The participants were not told if the injection they received is the vitamin supplement or a placebo. This experiment is using a_________ technique.
d. double-blind
Which of the following describes intrasubject counterbalancing in an experiment with two experimental conditions, A and B?
d. each participant experiences the following: condition A, condition B, condition B again, and condition A again (ABBA)
Suppose you do find an extraneous variable that could have great influence on your results, beyond the influence of the independent variable. You could increase the experiment's sensitivity by a
d. incorporating that extraneous variable as a second independent variable.
Changing the alpha level from .05 to .01 would
decrease the risk of a type I error and increase the risk of a type II error.
A key characteristic of grounded theory is
development of a theory based on empirical data.
Jordan wants to study a new intervention for helping 2nd graders learn to read better. Because the students in his sample differ from one another, he decides to match them based on gender, socioeconomic status, and IQ. Each matched set is then randomly assigned to the treatment conditions. Jordan is using matching by ______ in order to make his groups as similar as possible.
equating participants
In the context of extraneous variables, "history" refers to
events that can influence the dependent variable, that occur between the first and second measurement of that variable.
Sample size should be determined by a combination of which of the following factors? E
ffect size, alpha level, power
Colin has always heard the saying "blondes have more fun" and he wants to see if it's true. He's not sure what "have more fun" means so he just decides to find out if blondes are happier. He randomly samples blondes, brunettes, and redheads on his campus and administers a happiness scale to each. He conducts a one-way analysis of variance on the dependent variable of happiness and finds that the effect is statistically significant. To determine exactly which groups are significantly different he conducts 3 separate independent samples t-tests. What did Colin do wrong?
following up his ANOVA with multiple t-tests is inappropriate because it will increase the risk of a Type I error; he should have conducted a post-hoc test instead
Order effects and carryover effects differ in that
for order effects it is only the ordinal position of the treatment that matters.
The primary difference between a quasi-experimental design and a randomized experimental design is
he ability of the design to control for potential threats to internal validity
Of the major extraneous variables discussed in previous chapters, which is most likely a source of confounding in an interrupted time-series design?
history
What is the primary threat to internal validity that could confound the results of a regression discontinuity study?
history
In his study on canine cognition, Sherman guesses that German Shepherds are more likely to find hidden objects than other breeds. After he collects his data, he finds that German Shepherds perform at the same rate as other breeds. In this scenario, Sherman is engaging in
hypothesis testing
Which of the following may compromise the statistical conclusion validity of an experiment?
if the experiment has too few participants, thus reducing power
If an experiment is ecologically valid, then the effect of the treatment used in that experiment should be
independent of the experimental setting.
Jacqueline wanted to assess the reliability of ratings made of children's aggressive behavior so she had two students rate the degree of aggression displayed by each of 50 children while engaged in play. She then compared the ratings made by these two students and computed the degree of agreement between them. Jacqueline used what method of assessing reliability?
interrater reliability
Dr. Toris wants to test an incentive program to increase attendance in her classes. For the first 8 weeks of the semester she does not use the program, and records attendance rates each week. Then she institutes the incentive program for the last 8 weeks and continues to record attendance rate each week. She detects an increase in attendance over the last 8 weeks. This is an example of which experimental design?
interrupted time series
Reporting of details regarding participant characteristics, selection and assignment procedures
is important to enable other researchers to replicate your findings.
Which of the following is the LEAST important characteristic of a good control group?
it has the same number of participants as the experimental group
For her senior thesis, Nancy surveys fellow students about cheating. Her findings suggest that cheating is virtually non-existent on her campus. This is not consistent with the fact that, in the past semester, two dozen students have been found guilty by the Honor Board of cheating. Which of the following explanations would fall under the heading of "reactivity?"
it is known that participants in research like to present themselves as positively as possible, so students that cheated probably lied and did not report their cheating on the survey
If you are interested in any possible interaction effects between an extraneous variable and the independent variable, which of the following techniques you should use?
matching by making the extraneous variable into another independent variable
Kirsten runs an experiment for her Research Methods class in which she studies vocabulary learning in introductory-level French students. At the start of the semester, she assesses the students' knowledge of French vocabulary, then does the another assessment at the end of the semester. What statistical test should she use to see whether her group of French students significantly increased their knowledge of French vocabulary?
one way repeated measures analysis of variance
The most common reason for the use of quasi-experimental research designs is that
participants cannot be randomly assigned to groups.
Even though the one-group pretest-posttest design is inadequate, it has one methodological advantage over the one-group posttest-only design, and that is
pretest scores can be compared to posttest scores.
The nonequivalent comparison group design can yield several possible outcomes. In one scenario, the experimental group scored higher than the control group at the start of the experiment, and only the experimental group's scores increase from pretesting to post-testing. This could reflect an influence of the independent variable. However, it could also reflect
selection-maturation effect.
The nonequivalent comparison group design can yield several possible outcomes. In one scenario, the experimental group scores higher than the control group at the start of the experiment, and only the experimental group's scores increase from pretesting to posttesting. This could reflect an influence of the independent variable. However, it could also reflect
selection-maturation effect.
A variable shows reliability when
similar results are obtained each time it is measured.
Most psychological researchers want to know about behavior of people in general, but are often restricted to studying the college students immediately available to them on their campus. "All people" is the _________ population while "college students" is the ________ population.
target; experimentally accessible
In a nonequivalent comparison group study
the experimental group gets a pretest, then the experimental treatment, then a posttest.
In a nonequivalent comparison group study,
the experimental group gets a pretest, then the experimental treatment, then a posttest.
What is the difference between a within-participants design and a between-participants design?
the former involves all participants experiencing all levels of the independent variable
Dr. Kenji wants to determine whether his new phonics program helps children's reading comprehension. He gives a fifth grade class the program and also studies a second grade class that does not go through the program. He finds that the fifth graders read with better comprehension. Identify the confounding variable in this research design.
the grade the students are in
The defining characteristic of a factorial experimental design is
the manipulation of more than one independent variable
Power is
the probability of rejecting a false null hypothesis i
"External validity" of an experiment refers to the extent to which
the results of an experiment can be generalized across people, settings, and times, treatments, and outcomes.
One way to be sure that all "groups" in an experiment are equivalent except for their experience with the independent variable(s) is to use the same participants in all experimental conditions. However, this approach carries the danger of confounding in that
the sequence in which experimental conditions are experienced can affect performance.
