PSY 3213 Exam 2 Mavica
Pre-post designs
- The goal is to evaluate the effect of an intervening treatment or event by comparing observations made before versus after the treatment. -a pre-post design has no control group -One group of participants is observed (measured) before and after a treatment or event
• Random assignment (randomization)
-a random process (such as a coin toss) is used to assign participants to groups -goal is to ensure that all individuals have the same chance of being assigned to a group.
• Three-factor design
A research study involving three independent or quasi-independent variables.
• Telephone surveys
Advantage- The survey can be conducted from anywhere. It is possible to contact a fairly large number of participants in only a few days. Disadvantage- incredibly time-consuming -interviewer bias-Whenever a researcher has direct contact with participants, even over the telephone, there is a risk that the researcher will influence their natural responses by tone of voice or by rephrasing questions
Latin square
An n × n matrix in which each of n different items appears exactly once in each column and exactly once in each row. Used to identify sequences of treatment conditions for partial counterbalancing.
• A factorial study that is a purely experimental research design
Both factors are true independent variables that are manipulated by the researcher. Example: paper/screen time-controlled exp.
Identify the type of design being described in each scenario Robb lives in a community that experienced a powerful storm that destroyed a portion of the town. He is interested in how it has affected the ability of the residents to respond effectively to challenging situations. He recruits two groups of participants—those who were not directly affected by the storm and those who were affected, losing their homes and possessions. He has a between-subjects factor of task difficulty with three levels.
Combined strategy
• Guidelines for Constructing a Survey
Demographic questions should be placed at the end of the survey. Sensitive questions should be placed in the middle. Group questions with same topic. Format should be relatively simple. Vocabulary and language style should be easy to understand.
_____________ research identifies only whether a relationship exists between variables.
Differential
________ research identifies whether a causal relationship exists between variables.
Experimental
Margie believes that performance on her test of cognitive flexibility will be related to educational attainment, so she limits her participants to individuals who have a high school diploma or GED.
Holding constant
• Phase
In a single-case research design, a series of observations of the same individual under the same conditions.
Identify the type of relationship being described Carleen is studying the relationship between disordered eating and distorted body image. She finds that as scores on the measure of disordered eating increase, scores on the measure of distorted body image also increase.
Positive
Identify the way in which the correlation coefficient is being used Thomas looks at whether grade point average in middle school is related to grade point average as an undergraduate.
Prediction
• Type II error
The conclusion, based on a hypothesis test, that a result is not statistically significant when, in fact, a real effect or relationship does exist in the population. -Sample data does not show evidence of a significant effect when a real effect exists in the population.
Bar Graph
When the categories on the scale of measurement are not numerical values (nominal or ordinal scales), the frequency distribution is presented as a bar graph. -A bar graph is like a histogram except that a space is left between adjacent bars. -the height of each bar indicates the frequency associated with that particular category.
Factors
When two or more independent variables are combined in a single study, the independent variables
• Case history
a case study does not include any treatment or intervention
Individual differences
are personal characteristics that differ from one participant to another. -have the potential to produce high variability in the scores within a research study.
• Two-treatment designs
data measured on an interval or ratio scale-data analysis requires using a repeated-measures t or a single-factor ANOVA (repeated measures). ordinal scale data (or rank ordered data)-data is analyzed with a Wilcoxon test or a Sign test.
• Case study design
in-depth study and detailed description of a single individual (or a very small group). A case study may involve an intervention or treatment administered by the researcher.
• Single-subject designs
-Experimental research designs that use the results from a single participant or subject to establish the existence of a cause-and-effect relationship. Also known as single-case designs. -Must manipulate an IV and control extraneous variables to prevent alternative explanations for the research results. -advantage is that they allow researchers to conduct experiments in situations where a single individual is available or is being treated, observed, and measured. -most single-case designs were developed by behaviorists examining operant conditioning. -incorporates elements of descriptive case studies and quasi-experimental time-series designs
• Open-ended questions
-Introduce a topic and allow participants to respond in their own words. -Advantage -allows an individual the greatest flexibility in choosing how to answer -Disadvantage different participants may approach the question from entirely different perspectives, leaving you with answers that are impossible to compare or summarize. -answers are often difficult to summarize or analyze with conventional statistical methods. -may be limited by a participant's ability or willingness to express his or her thoughts.
• Disadvantages of within-subjects design
-May lead to time-related factors which influence the subjects' scores -Participant attrition- the loss of participants that occurs during the course of a research study conducted over time.
Restricted questions
-Present a limited number of response alternatives. -Like a multiple-choice question, typically asks the participant to select the best or most appropriate answer in a series of choices -questions produce a limited and predetermined set of responses, they are easy to analyze and summarize. -the data are tabulated and reported as percentages or proportions of participants selecting each alternative. -It also is possible to obtain quantitative information from restricted questions by using an ordered set of response alternatives -an element of open-endedness can be allowed in a restricted question by including a blank category where participants are free to fill in their own responses
• Multiple-Treatment Designs: Advantages
-Primary advantage of the multiple treatment design is the data are more likely to reveal the functional relationship between the two variables. -Produces a more convincing demonstration of a cause-and-effect relationship than a two-treatment design
• Regression
-Regression- A statistical technique used for predicting one variable from another. -Goal: to find the equation that produces the most accurate predictions of Y (the criterion variable) for each value of X (the predictor variable).
• Rating-scale questions
-Require selection of a numerical value on a predetermined scale. -The numerical scale typically presents a range of response alternatives from very positive to very negative. A common example uses a 5-point scale which individuals rate their level of agreement or disagreement -Advantage participants usually find them easy to understand and easy to answer. they produce numerical values that can be treated as measurements from an interval scale.
• Advantages of within-subjects design
-Requires relatively few participants. -Eliminates problems based on individual differences
• Controlling Time
-Shortening the time between treatments increases the likelihood that order effects will influence results. -Increasing the time between treatments increases the risk of time-related threats to internal validity.
• Matching groups (matched assignment
-The assignment of individuals to groups so that a specific variable is balanced or matched across the groups. -
• Type I error
-The conclusion, based on a hypothesis test, that a result is statistically significant when, in fact, there is no effect (no relationship) in the population. -A false report: a researcher finds evidence for a significant result when there is no effect (no relationship) in the population.
Equivalent Groups
-The researcher has both the opportunity and the responsibility to create groups that are equivalent. -The separate groups must be: Created equally-. The process used to obtain participants should be as similar as possible for all of the groups. Treated equally-. Except for the treatment conditions that are deliberately varied between groups, the groups of participants should receive exactly the same experiences. Composed of equivalent individuals.- The characteristics of the participants in any one group should be as similar as possible to the characteristics of the participants in every other group.
• Trend
-a consistent increase (or a consistent decrease) in the magnitude of behavior across the series of observations that make up the phase
• Strengths of the Correlational Research Strategy
-can identify variables and describe relationships between variables -allows researchers an opportunity to investigate variables that would be impossible or unethical to manipulate. -researcher simply records what exists naturally -high external validity
• Holding variables constant
-example, if a researcher suspects that gender differences between groups might confound a research study, one solution is to eliminate gender as a variable. By using only female participants, a researcher can guarantee that all of the groups in a study are equivalent with respect to gender; all groups are all female.
• Descriptive Research
-is not concerned with relationships between variables but rather with the description of individual variables. The goal is to describe a single variable or to obtain separate descriptions for each variable when several are involved. - is extremely useful as preliminary research (i.e., in the early stages of research) and in its own right. -typically involves measuring a variable or set of variables as they exist naturally -can help us capture interesting, naturally occurring behavior.
Attrition
-participant withdrawal from a research study before it is completed -big differences in attrition rates between groups can create problems -if more participants drop out of one group than the other, there is a risk that the two groups will no longer be similar.
• Habituation
-repeated exposure of participants to the observer's presence until it is no longer a novel stimulus. •Behaviors that are disrupted or influenced by the presence of an observer can be addressed by concealing the observer. •Or, participants can be habituated to the observer's presence.
• Participant observation
-the researcher engages in the same activities as the people being observed in order to observe and record their behavior. -needed in situations in which inconspicuous observation is not possible. -Observe behaviors that are not open to observation and information that may not be accessible to outside observation. -The results have high external validity because the behaviors are examined in real-world settings, not laboratories. -observer gains a unique perspective, obtaining insight into behavior not obtainable by observing from afar. -Limitations -extremely time-consuming -interacting with the participants and identifying closely with the individuals in the study, an observer may lose objectivity. -is potentially dangerous for the observer. - the observer may inadvertently alter participants' behavior by directly interacting with them
• Observational Research Design
-the researcher observes and systematically records the behavior of individuals to describe the behavior. -Two problems: The behaviors can not be disrupted or influenced by the presence of an observer. Observations are based, in part, on a subjective judgment.
• Correlations
.a statistical value that measures and describes the direction and degree of relationship between two variables. Correlations measure and describe three aspects of the relationship between two variables: The direction The form The degree of consistency, or strength, of the relationship.
• Contrived observation (structured observation)
(structured observation)- Researcher sets up a situation likely to produce the desired behavior in participants. -Often, such studies are conducted in laboratory settings - may also take place in a natural but "set up" arena: a field setting (which the participant perceives as a natural environment) arranged by the researcher -Advantage: Do not have to wait for behaviors to occur naturally. Disadvantage: The environment is less natural - the behavior may be as well.
• Standard error
- A measure of the average or standard distance between a sample statistic and the corresponding population parameter. -Provides a measure of how much difference it is reasonable to expect between a statistic and a parameter. -The standard error tells you how much discrepancy to expect.
Which of the following statements regarding factorial design are true?
-A 2 x 2 factorial and a 3 x 5 factorial are both two-factor designs. -In a factorial design, the independent variables are referred to as factors.
Single-factor multiple-group design
-A research design comparing more than two groups of participants (or groups of scores) representing more than two levels of the same factor. -Analyzed with a single-factor analysis of variance (ANOVA) (independent measures). -Provides stronger evidence for a real cause-and-effect relationship than a two-group design -When the ANOVA concludes that significant differences exist, some form of post hoc test or post test is used
• Matched-subjects design
-A research design comparing separate groups of individuals in which each individual in one group is matched with a participant in each of the other groups. The matching is done so that the matched individuals are equivalent with respect to a variable that the researcher considers to be relevant to the study.
Two-group mean difference
-A research design comparing two groups of participants or two groups of scores representing two levels of a factor. Also known as the two-group design. -Independent-measures t test shows if there is a significant difference between the means. -Primary advantage: simplicity -Primary disadvantage: provides little information
• Survey research design
-A research study that uses a survey to obtain a description of a particular group of individuals -efficient ways to gather large amounts of information. -goal of the survey research design is to obtain an accurate picture of the individuals being studied -provides a "snapshot" of the group at a particular time.
• A factorial study that is purely a within-subjects design
-A single group of individuals participates in all the separate treatment conditions. Disadvantages-the number of different treatment conditions that each participant must undergo can be time-consuming and cause participant attrition -series of treatment conditions can increase the potential for testing effects (such as fatigue or practice effects) and make it more difficult to counterbalance the design to control for order effects. Advantages-require only one group of participants and eliminate or greatly reduce the problems associated with individual differences
Diffusion
-A threat to internal validity that occurs when a treatment effect spreads from the treatment group to the control group, usually from participants talking to each other.
• Naturalistic observation
-A type of observation in which a researcher observes behavior in a natural setting as unobtrusively as possible. Also known as nonparticipant observation. -useful in providing insight into real-world behavior. -high degrees of external validity because the behavior is examined in real-world settings as opposed to laboratories -useful for examining behaviors that, for practical or ethical reasons, cannot be manipulated by the researcher. -Limitation time needed to conduct this type of research. observer must take extra care not to disrupt or influence the behavior being observed
• Multiple-Treatment Designs: Disadvantages
-Disadvantage of multiple treatment design is that a researcher may create too many treatments. The distinction between treatments may become too small to generate significant differences. -May increase attrition if more time is required of participants. -Counterbalancing is more difficult as the number of treatments increases
• Confounding from environmental variables
-Environmental variables are any characteristics of the environment that may differ. -If these variables are different between groups, then the experiment is confounded by environmental variables. -Example- one group may be tested in a large room and another group in a smaller room. -variable may cause differences between groups that cannot be attributed to the independent variable.
How can factorial designs correctly address specific research issues?
1.Using a participant variable such as age or gender as a second factor can separate participants into more homogeneous groups and thereby reduce variance in a between-subjects design. 2. When the order of treatments is used as a second factor in a counterbalanced within-subjects design, it is possible to measure and evaluate the order effects.
Cross-sectional developmental research design-
A developmental design comparing different groups of individuals, each group representing a different age. Cohorts-are individuals who were born at roughly the same time and grew up under similar circumstances. Cohort or generation effects- Differences between age groups that are caused by characteristics or experiences other than age. Also called generation effect. -Cohort effects are more likely when there are large age differences between groups
Longitudinal developmental research design-
A developmental research design that examines development by making a series of observations or measurements over time. Typically, a group of individuals who are all the same age is measured at different points in time.
• Mixed design
A factorial study that combines two different research designs, such as between-subjects and within-subjects, in the same factorial design.
• Correlational research
A general approach to research that involves measuring two or more variables for each individual to describe the relationship between the variables. -no attempt is made to explain the relationship. -is no attempt to manipulate, control, or interfere with the variables
• Scatter Plot
A graph that shows the data from a correlational study each individual is represented by a single point with a horizontal coordinate determined by the individual's X score and the vertical coordinate corresponding to the Y value -allows you to see the characteristics of the relationship between the two variables.
• Standard deviation
A measure of variability that describes the average distance from the mean; obtained by taking the square root of the variance. -When the scores are clustered close to the mean, the standard deviation is small; when the scores are scattered widely around the mean, the standard deviation is large. -general rule, roughly 70% of the scores in a distribution are within one standard deviation of the mean, and roughly 95% of the scores are within two standard deviations. -the sample standard deviation is usually identified by the letter s,
• Multiple-baseline across subjects
A multiple-baseline design in which the initial baseline phases correspond to the same behavior for two separate participants -still examine the behavior of each individual, separately. Specifically, we do not consider the two participants to be a group and attempt to examine the average behavior for the group. -begins with a baseline phase with simultaneous observations, beginning at the same time, for both participants. After a baseline pattern is established for both participants, the treatment phase is initiated for one participant only. the baseline phase is continued for the second participant. Finally, the treatment phase is initiated for the second participant, but at a different time from that at which treatment is begun for the first participant.
• Multiple-baseline across situations
A multiple-baseline design in which the initial baseline phases correspond to the same behavior in two separate situations. -begin baseline measurements for both situations simultaneously, and then administer treatment at two different times for the two different situations.
• Multiple-baseline across behaviors
A multiple-baseline design in which the initial baseline phases correspond to two separate behaviors for the same participant. -the same treatment is used for each of the different behaviors -.After clear baseline patterns are established for both behaviors, the treatment is started for one of the behaviors and baseline observations continue for the second behavior. After a short period, the treatment is started for the second behavior.
What is the difference between nonexperimental and quasi-experimental designs
A nonexperimental design makes little or no attempt to minimize threats. A quasi-experimental design makes some attempt to minimize threats to internal validity—is almost, but not quite, a true experiment.
between-subjects design
A research design in which each of the different groups of scores is obtained from a separate group of participants. Also known as an independent-measures design. -participant's score is not influenced by such factors as: -practice or experience gained in other treatments; -fatigue or boredom from participating in a series of different treatments;contrast effects that result from comparing one treatment to another -One disadvantage is that they require a relatively large number of participants and individual differences
within-subjects design
A research design in which the different groups of scores are all obtained from the same group of participants. Also known as repeated-measures design. -All participants go through the entire series of treatments but not necessarily in the same order.
• Nonequivalent control group design
A research design in which the researcher does not randomly assign individuals to groups but rather uses preexisting groups.
• Two-factor design
A research study involving two independent or quasi-independent variables.
• Differential research design.
A research study that compares preexisting groups.
• Single-factor design
A research study with one independent variable or one quasi-independent variable.
• Multiple-baseline design
A single-case design that begins with two simultaneous baseline phases, then initiates a treatment for one baseline, and, at a later time, initiates the treatment for the second baseline.
• Reversal design
A single-case experimental design consisting of a series of phases including a baseline phase followed by a treatment phase and at least one replication of a baseline followed by a treatment. -are done over time in a single individual. -
• ABAB design
A single-case experimental design consisting of four phases: a baseline phase, a treatment phase, withdrawal of treatment which is a return (or reversal) baseline phase, and a second treatment phase. most commonly used reversal design. -goal is to demonstrate that the treatment causes a change in behavior
• Central tendency
A statistical measure that identifies a single score that defines the center of a distribution. -Goal: to identify the value that is most typical or most representative of the entire group.
• Multiple regression
A statistical procedure for studying multivariate relationships. Example: academic performance can be explained or predicted from a set of predictor variables such as IQ and motivation. Control the influence of other, potentially confounding variables. -Predictor variables only predict. Relationships can be described—not explained. -the language used to discuss and report the results from a multiple regression can be misleading.
• Parameter
A summary value that describes a population A common example of a parameter is the average score for a population.
Compensatory equalization
A threat to internal validity that occurs when an untreated group demands to receive a treatment that is the same as or equivalent to the treatment received by another group in the research study.
Compensatory rivalry
A threat to internal validity that occurs when an untreated group learns about special treatment received by another group, then works extra hard to show they can perform just as well as that group.
Resentful demoralization
A threat to internal validity that occurs when an untreated group learns of special treatment given to another group, and becomes less productive and less motivated because they resent the other group's expected superiority.
• Internet surveys
Advantage -Internet surveys provide an economical and efficient medium for reaching a large number of potential respondents. -a researcher has greater access to participants with a particular characteristic -the flexibility in presenting questions and response alternatives. Disadvantage -Nonresponse bias- In survey research, individuals who return the survey are not usually representative of the entire group who received the survey. Nonresponse bias is a threat to external validity. No ability to control or even determine the composition of the sample. -Internet surveys are controlled best when they are administered to a closed group of e-mail users
• In-person surveys and interviews
Advantage- Most efficient method for administering a survey to a group. A one-on-one interview is valuable too. -interviews are reserved for a very small group of specially selected individuals, often called key informants these are people who have unique perspectives on the issues or unique access to information -provides an opportunity for follow-up questions, and it is possible to explore complex issues more fully Gather information from individuals who are unable to read and answer printed questions. Disadvantage- Can be time consuming. Interviewer bias can distort the results.
• Mail surveys
Advantage- Very convenient and nonthreatening. Can complete the survey at their own convenience and can be relatively confident that responses are anonymous and confidential. Disadvantage- survey is anonymous means that a researcher can never be sure exactly who in the household completed and returned the survey. -Can be expensive and time-consuming. Response rates tend to be very low response rates can be significantly improved if a good cover letter accompanies the survey, includes a gift or token of appreciation with each survey, giving participants advance warning of the survey, then providing a follow-up reminder after the survey has been received
· Hypothesis test
An inferential statistical procedure that uses sample data to evaluate the credibility of a hypothesis about a population. A hypothesis test determines whether research results are statistically significant. ensures the internal validity of a study. Goal: rule out chance as a plausible explanation for the results. Attempts to distinguish between two explanations for the sample data: -Patterns in the data representing systematic relationships among variables in the population. -Patterns in the data produced by random variation from chance or sampling error.
• Frequency distributions
An organized display of a set of scores that shows how many scores are located in each category on the scale of measurement. Can be a table or a graph. -advantage of a frequency distribution is that it allows a researcher to view the entire set of scores. - disadvantage is that constructing a frequency distribution without the aid of a computer can be somewhat tedious, especially with large sets of data.
Miles is studying visual memory function. He has recruited research participants from introductory psychology students. He shows a randomly selected one-third of the participants emotionally upsetting photos, shows another one-third very happy photos, and shows the last one-third neutral photos. He then tests visual memory and compares the scores of the groups. What design is Miles using?
Between-subjects
Nonequivalent group design
Compare preexisting groups of individuals
• Identifying an Interaction in a Data Matrix
Compare the mean differences in any individual row with the mean differences in other rows (applies to columns also). -The size and the direction of the differences in one row are the same as the corresponding differences in other rows ►no interaction. -Differences change from one row to another ► evidence of an interaction.
Pre-Post Designs
Compares two or more scores for one group of participants
Several students in the comparison group figure out that they are not getting the new intervention and complain to an administrator. In order to avoid problems, the administrator takes it on himself to see to it that the students in the comparison group get his version of Faye's new treatment.
Compensatory equalization
When a handful of students in the comparison group learn that they are not getting the "real" treatment, they get angry and channel their anger into doing as well as possible on the tests at the end of the intervention.
Compensatory rivalry
Two major sources of potential confounds for within-subjects
Confounding from environmental variables. Confounding from time-related variables.
Within-subjects designs can control environmental threats to internal validity using the same techniques used in between-subjects designs
Control environmental threats to internal validity by randomization holding them constant matching across treatment conditions
___________________ research identifies whether a relationship exists between variables and, if one does, describes the pattern and strength of the relationship.
Correlational
Which statements are true with regard to counterbalancing?
Counterbalancing can increase within-treatment variance Complete counterbalancing can greatly increase the number of participants required.
The students talk to each other, figure out what they think is special about the new methods, and create a do-it-yourself treatment based on the experimental treatment.
Diffusion
Post hoc test or post-test
Follow-up hypothesis tests done after an analysis of variance to determine exactly which mean differences are significant.
• Statistical Analysis of Factorial Designs
For two between-subjects factors, the correct choice is an independent-measures two-factor ANOVA (see p. 490). If only one of the two factors is between-subjects, then you must specify which it is and use a mixed-design two-factor ANOVA (see p. 492). For two within-subjects factors, you use a repeated-measures two-factor ANOVA.
Calculating a Correlation Coefficient
Form- Linear relationship- The data points in the scatter plot tend to cluster around a straight line. Pearson correlation- A correlation used to evaluate linear (straight-line) relationships. -monotonic relationship.-A relationship that is consistently one-directional, either consistently positive or consistently negative -the amount of increase/decrease need not be constantly the same size -Spearman correlation- used to measure and describe monotonic relationships when both variables are ranks from an ordinal score or have been transformed to ranks
• Confounding from individual differences
Groups with different characteristics threaten the internal validity of study. -Individual differences are any participant characteristics that can differ from one participant to another. -If these characteristics are different from one group to another, then the experiment is confounded. -Example- the participants in one group may be older, smarter, taller, or have higher socioeconomic status than the participants in another group -variables may produce differences between groups that can compromise the research results.
Micah has an intervention designed to encourage young homosexual men to get tested for HIV and other sexually transmitted infections. In the midst of his intervention, a well-known actor discloses that he is HIV positive, and he encourages everyone to be tested and to know their own status and the status of others with whom they are intimate.
History
• Predictor variable
In a correlational study, a researcher often is interested in the relationship between two variables to use knowledge about one variable to help predict or explain the second variable. In this situation, the first variable is called the predictor variable. -usually relatively simple and well defined.
• Criterion variable
In a correlational study, a researcher often is interested in the relationship between two variables to use knowledge about one variable to help predict or explain the second variable. In this situation, the second variable (being explained or predicted) is called the -usually relatively complex and unknown
• Statistical significance of a correlation
In a correlational study, the correlation in the sample is large enough that it is very unlikely to have been produced by random variation, but rather represents a real relationship in the population.
• Main effect
In a factorial study, the mean differences among the levels of one factor. -a two-factor study has two main effects; one for each of the two factors. -
• Null hypothesis
In a hypothesis test, a statement about the population(s) or treatments being studied that says there is no change, no effect, no difference, or no relationship. -Any patterns in the sample are nothing more than chance (sampling error).
• Alpha level (level of significance)
In a hypothesis test, the criterion for statistical significance that defines the maximum probability that the research result was obtained simply by chance. -A hypothesis test with an alpha level of .01, for example, means that the test demands that there is less than a 1% (.01) probability that the results are caused only by chance.
• Statistically significant result
In a research study, a result or treatment effect that is large enough to be extremely unlikely to have occurred simply by chance.
• Practical significance
In a research study, a result or treatment effect that is large enough to have value in a practical application. Also known as clinical significance. -the results from a single-case study tend to have practical significance, although they typically are not evaluated in terms of statistical significance.
· Statistically significant result
In a research study, a result that is extremely unlikely (as defined by an alpha level, or level of significance) to have occurred simply by chance.
Progressive error
In a research study, changes in the scores observed in one treatment condition that are related to general experience in a research study over time, but not to a specific treatment or treatments. Common kinds of progressive error are practice effects and fatigue.
• Treatment observations
In a single-case research study, observations or measurements made while a treatment is being administered. -a treatment phase is usually identified by the letter B. -Specifically, when a study contains two or more treatments, B identifies the first treatment condition, and C, D ect. identify other treatments. --when a study contains modifications of a basic treatment, B identifies the basic treatment, and the different modifications are called B1, B2 ect.. -when one phase involves administering two or more treatments simultaneously, the single phase can be identified by a pair of letters representing the two different treatments ex-BC
• Baseline observations
In a single-case research study, observations or measurements made while no treatment is being administered. -a baseline phase is identified by the letter A
• Phase change
In a single-cases research study, a change in the conditions from one phase to another. Accomplished by implementing a treatment, withdrawing a treatment, or changing a treatment. A new phase, during which the researcher collects a series of observations under a new set of conditions. -, a phase must consist of a minimum of three observations. -decision to make a phase change is based on the participant's responses. If the responses establish a clear pattern, then a change is appropriate. If the responses indicate a serious problem, then a change is necessary.
• Counterbalancing
In a within-subjects design, a procedure to minimize threats from order effects and time-related factors by changing the order in which treatment conditions are administered from one participant to another so that the treatment conditions are matched with respect to time. The goal is to use every possible order of treatments with an equal number of individuals participating in each sequence.
• Frequency method
In behavioral observation involves counting the instances of each specific behavior that occur during a fixed-time observation period. For example, the child committed three aggressive acts during the 30-minute period. -often well suited for specific behaviors but can lead to distorted measurements in some situations.
Harry is conducting research that includes using physiological measures like EEGs. His research assistant is uncomfortable doing the setup for EEGs, so with his many years of experience, Harry does all of the setups for the first phase of the study but makes his research assistant do the setups for the second phase.
Instrumentation
Identify the type of effect that is being described in each scenario Frank finds that delay of reward has a far greater effect on learning in the low-reward condition than in the high-reward condition.
Interaction
Identify the type of design being described in each scenario Elaine studies the effects of natural disasters. After a February blizzard shuts down a large part of the state, many newscasters speculate about a baby boom the following November. Elaine decides to look at birthrates in September, October, November, December, and January to find out whether there is, indeed, a boom of blizzard babies.
Interrupted time-series
What are some of the advantages of a between-subjects design?
It can be used to address a wide variety of questions. It allows each individual score to be independent of all other scores.
Categorize the strength of the relationship Artie finds a correlation of 0.62 between scores on a test of reading skills and scores on a test of spelling skills.
Large
Identify the type of effect that is being described in each scenario Frank finds that learning is faster with high-reward conditions than with low-reward conditions.
Main effect
• Advantages of Single-Case Designs
Make experimental clinical research compatible with routine clinical practice. Establish cause-and-effect relationships between treatments and behaviors using only a single participant. Makes it possible to integrate experimental research into applied clinical practice. -flexibility. If a participant fails to respond to treatment, for example, the researcher is free to modify the treatment or change to a new treatment without compromising the experiment. -allow a clinician/researcher to individualize treatment to meet the needs of a specific client. -allows for the detailed description and individualized treatment of a single participant
Vincent knows that performance on his test of cognitive flexibility is related to age, so he makes sure that for every person of a specific age in his treatment group, there is a person of the same age in his comparison group.
Matching
Shawna has developed an intervention to help young children who are struggling with quantitative skills. At the time of her initial testing, she realizes that the children are learning but that they are learning more slowly than are other students.
Maturation
Categorize the strength of the relationship Clarke finds a correlation of -0.32 between scores on a test of knowledge of tobacco effects and scores on a test of positive attitudes toward tobacco use.
Medium
Identify the type of design being described in each scenario Rhonda is studying the effects of hunger on academic performance. She uses hunger as a within-subjects factor, starting her subjects out with a very small breakfast and testing them at two-hour intervals throughout the day without any additional meals or snacks. She has a between-subjects factor of task difficulty, with three levels: easy, medium, and hard.
Mixed design
Identify the type of relationship being described Leo is studying health decision-making and finds that, as the number of negative beliefs about a given behavior (for example, the number of negative beliefs about eating highly processed foods) increases, the frequency of the associated behavior (for example, the frequency of eating high-fat foods) decreases.
Negative
• Graphing the results of a two-factor study
Nonparallel lines (lines that cross or converge) indicate an interaction between the two factors. Note: A statistical test is needed to determine whether the interaction is significant.
· Response set
On a rating-scale question, a participant's tendency to answer all (or most) of the questions the same way. -One rationalization is that they do not feel strongly about any of the items, so they really are neutral. (A more likely explanation is that they simply want to finish quickly.) -Another possibility is that a participant may use the agree category for all responses except to those few items where there is serious disagreement.
• A factorial study that is a mixed design
One between-subjects factor and one within-subjects factor Ex:Durso, Luttrell, and Way (2015). The researchers showed participants a series of photographs of positive and negative images to create a within-subjects factor (positive/negative). The researchers manipulated acetaminophen by dividing the participants into two groups and having one group given 1,000 milligram dose and the other group given a placebo, creating a between-subjects factor (acetaminophen/placebo). The participants in both groups rated the pleasantness/unpleasantness of each photograph.
o Pretest-posttest nonequivalent control group design (quasi-experimental)
One group is measured twice ►once before a treatment is administered and once after. A second group is measured at the same two times but does not receive any treatment.
Posttest-only nonequivalent control group design-
One group serves in the treatment condition. A second group of similar but nonequivalent participants is used for the control condition. The control group is measured at the same time but receives no treatment
Identify the type of design being described by each scenario Julie is contacted by a community-based organization that needs to evaluate a self-esteem building intervention it has created for use in its after-school program. Unfortunately, the program has already begun, so Julie arranges to measure the children's self-esteem after the intervention has been completed and compares this data to measures of self-esteem she gets from another after-school program where the children have not gotten the self-esteem building intervention.
Posttest-only nonequivalent control group
Identify the type of design being described in each scenario Darleen has developed a new training workshop for aides who work with nursing home patients with dementia. She tests their knowledge at the start of the workshop and again at the end.
Pretest-posttest
Identify the type of design being described by each scenario Colleen is interested in preventing adolescents from ever starting to use tobacco. She has the opportunity to work with two health classes at a middle school. One class gets the traditional tobacco-prevention programming, and the other half gets Colleen's new program. Knowledge about and attitudes toward tobacco are assessed in both groups, both before and after the programming.
Pretest-posttest nonequivalent control group
• Using a Participant Variable as a Second Factor
Purpose is to reduce the variance within groups by using the specific variable as a second factor ► creates a two-factor study. Greatly reduces individual differences within each group. Does not sacrifice external validity. Example: Bartholow and Anderson (2002) repeated previous research studies examining the effect of media violence on aggressive behavior and then extended the study by adding gender as a second factor.
George relies on the flip of a coin to assign participants to the treatment or comparison group.
Random assignment
What are three primary techniques to limit confounds?
Random assignment (randomization) Matching groups (matched assignment) Holding variables constant
Rory has developed an intervention for individuals with obsessive-compulsive disorder. Before he starts his intervention, he administers a test designed to measure the severity of obsessions and compulsions, and the group has an extremely high average score—well above the mean score that would be expected for individuals with obsessive-compulsive disorder. Following the intervention, there is a reduction in the groups' score on the test.
Regression
Identify the way in which the correlation coefficient is being used Mona has research participants complete her anxiety scale on two different occasions, six weeks apart.
Reliability
Identify what tests would be used with the types of design and data described Lois is studying the effectiveness of three different stress-reducing apps using a within-subjects design. Her outcome measure is the severity of stress reported by participants, an interval level measure.
Repeated-measures ANOVA only
Identify what tests would be used with the types of design and data described Angelo is studying the effects of reward magnitude on children learning spelling words using a within-subjects design. Children get paid either $0.50 or $1 for every word they spell correctly on their weekly spelling tests, and the outcome measure is the number of words spelled correctly, a ratio level measure.
Repeated-measures t test or repeated-measures ANOVA
Several students in the comparison group respond quite differently to learning they are not in the treatment group and just give up, doing poorly on the tests at the end of the intervention.
Resentful demoralization
Categorize the strength of the relationship Donna finds a correlation of -0.11 between scores measuring personality rigidity and scores on a test of cognitive flexibility.
Small
• Inferential statistics
Statistical methods used to determine when it is appropriate to generalize the results from a sample to an entire population. -general purpose for inferential statistical techniques is to use sample statistics as the basis for drawing general conclusions about the corresponding population parameters.
• Descriptive statistics
Statistical methods used to organize, summarize, and simplify the results obtained from research studies. -Examples of descriptive statistics include organizing a set of scores into a graph or a table and calculating a single value, such as the average score, that describes the entire set.
• Sample statistic
The data from the research study are used to compute sample statistics corresponding to the parameters specified in the null hypothesis. -For example, if the null hypothesis states that there is no difference between two population means, the sample statistic would be the difference between two sample means
• Frequency Distribution Graphs
The graph shows the scale of measurement (set of categories) along the horizontal axis and the frequencies on the vertical axis. When the measurement scale consists of numerical values, there are two options for graphing the frequency distribution o Histogram o Polygon
• Participant attrition
The loss of participants that occurs during the course of a research study conducted over time. Attrition can be a threat to internal validity. Also known as participant mortality.
• Coefficient of determination
The squared value of a correlation that measures the percentage of variability in one variable, which is determined or predicted by its relationship with the other variable. -Measures the percentage of variability in one variable that is determined, or predicted, by its relationship with the other variable. -a correlation is typically identified by the letter r, the coefficient of determination is
• A factorial study that is purely a between-subjects design
There is a separate group of participants for each of the treatment conditions. Disadvantages- -require a large number of participants. -individual differences can become confounding variables and increase the variance of the scores. -Advantage -completely avoids any problem from order effects because each score is completely independent of every other score.
Identify the type of design being described in each scenario Emmett works with adults with severe persistent mental illness. He is well aware that, because of their illnesses, their self-esteem can vary substantially from time to time. He has developed an app that he believes will help maintain some stability in their self-esteem. In order to have more stability in his measurements, he measures self-esteem on a biweekly basis, starting a month before he gives the research participants access to the app, and then measures self-esteem biweekly for another six weeks.
Time-series
• Behavior categories
To address the second problem, subjectivity, researchers typically employ three interrelated devices to help ensure the objectivity of their behavioral observations. -Categories of behavior to be observed (such as group play, play alone, aggression, social interaction). -before observation begins, we identify the categories of behavior we want to observe and then construct a list of specific behaviors that are examples for each category. -A preexisting list enables observers to know exactly what to look for and how to categorize each behavior. -a set of pre-established behavior categories provides a clear operational definition of each construct being examined.
• Experimental Factorial design
Two or more IVs (factors) are manipulated. Advantages: -Creates a more realistic situation than examining a single factor in isolation. -Can see how individual factors as well as the group of factors, acting together, influence behavior.
What methods can be used to minimize variance within a treatment group?
Use a large sample size. Use random assignment and matching. Standardize the treatment setting.
Identify the way in which the correlation coefficient is being used Victor looks at the relationship between his new test of emotional intelligence and a well-established measure of emotional intelligence.
Validity
What is the primary disadvantage of the between-subjects design?
Vulnerability to individual differences
identify which design would be better—within-subjects or between-subjects. Thom is studying individuals with a rare disorder and needs to minimize the number of research participants required.
Within-subjects
identify which design would be better—within-subjects or between-subjects. Twyla wants to minimize the potential impact of individual differences.
Within-subjects
• The directionality problem
a problem encountered in correlational studies; the researchers find a relationship between two variables, but they cannot determine which variable may have caused changes in the other variable
• Sampling error
a sample does not provide a perfectly accurate picture of its population; that is, there is some discrepancy, or error, between the information available from a sample and the true situation that exists in the general population.
Time-series design
a series of observations for each participant before a treatment or event and a series of observations after the treatment or event. - Interrupted time-series design-A study in which the intervening event is not manipulated by the researcher
• Statistic
a summary value that describes a sample. A common example of a statistic is the average score for a sample. -Describe or summarize the entire set of scores in the sample. Provide information about the corresponding summary values for the entire population.
• Test statistic
a summary value that measures the degree to which the sample data are in accordance with the null hypothesis. -Typically, a large value for the test statistic indicates a large discrepancy between the sample statistic and the parameter specified by the null hypothesis, and leads to rejecting the null hypothesis.
identify which design would be better—within-subjects or between-subjects. Jeff wants to eliminate the possibility of order effects.
between-subjects.
• Disadvantages of Single-Subject Designs
cause and effect relationship is demonstrated only for one participant. -requirement for multiple, continuous observations -absence of statistical controls. Problems can arise if there is any ambiguity in the graphed results Reliance on graphs to demonstrate that treatment effects are real. Treatment effects must be large and immediate to produce a convincing graph.
• Stability
consistency of the pattern -When the data points form a straight line with only minor deviations, data is said to be stable, and pattern is easy to see. -data points do not have to form a perfectly straight line to be considered stable; some variability is allowed, but it should be relatively small. -if there are large differences (high variability) from one observation to the next, so that no obvious pattern emerges, the data are said to be unstable. -
Alma studies creativity and is studying age-associated changes in self-censorship, which is often thought of as suppressing creativity. She has groups of subjects who are 6 to 8 years old, 9 to 10, 11 to 12, 13 to 14, and 15 to 16. Her design is
cross-sectional
Identify the type of design being described by each scenario Lisa wants to know whether any of the stereotypes about dog and cat owners are true. She recruits a group of individuals who describe themselves as dog people and a group who describe themselves as cat people and gives both groups a personality test.
differential
When examining the relationship between two variables in a correlational study, it is not possible to tell which variable is the cause and which is the effect. This is referred to as the __________ problem.
directionality
• Weaknesses of the Correlational Research Strategy
does not produce a clear and unambiguous explanation for the relationship -Cannot assess causality Low internal validity
• Partial counterbalancing
each treatment condition occurs first in the sequence for one group, occurs second for another group, etc
• Interaction
exists between factors when the effects of one factor depend on the different levels of a second factor.
• Single-case time-series designs
focus on a single case, rather than a group of participants Example: a therapist could monitor instances of compulsive behavior in one client for 3 weeks before therapy and for 3 weeks after.
Another term for the between-subjects design is ____________ design.
independent measures
• Interval method
involves dividing the observation period into a series of intervals and then recording whether a specific behavior occurs during each interval. For example, the 30-minute observation period is divided into thirty 1-minute intervals. The child was observed in group play during 12 of the intervals. -provides a way to balance frequency and duration to obtain a more representative measurement.
• Individual sampling
involves identifying one participant to be observed during the first interval, then shifting attention to a different individual for the second interval, and so on.
• Event sampling
involves identifying one specific event or behavior to be observed and recorded during the first interval, then shifting attention to a different event or behavior during the second interval, and so on, for the full series of intervals.
• Archival research
involves looking at historical records (archives) to measure behaviors or events that occurred in the past. -does not involve the direct observation of behaviors but follow the same rules as used for behavioral observation. -Establish behavioral categories. -Use the frequency method, the duration method, or the interval method for obtaining numerical scores. -Employ multiple observers for at least part of the measurement process to obtain a measure of inter-rater reliability.
• Time sampling
involves observing for one interval, then pausing during the next interval to record all the observations. The sequence of observe-record-observe-record is continued through the series of intervals.
• Combined strategy
involves one factor that is a true independent variable consisting of a set of manipulated treatment conditions, and a second factor that is a quasi-independent variable that typically falls into one of the following categories. -The second factor is a preexisting participant characteristic such as age or gender. -The second factor is time Ex-(Bartholow & Anderson, 2002). Violent game vs Nonviolent game. In the study, the researchers manipulated the level of violence in the video game, so this factor is a true independent variable. The second factor in the study is gender, which is a preexisting participant variable and, therefore, a quasi-independent variable.
• Duration method
involves recording how much time an individual spends engaged in a specific behavior during a fixed-time observation period. For example, the child spent 18 minutes playing alone during the 30-minute period. -often well suited for specific behaviors but can lead to distorted measurements in some situations.
• Content analysis
involves using the techniques of behavioral observation to measure the occurrence of specific events in literature, movies, television programs, or similar media that present replicas of behaviors. -does not involve the direct observation of behaviors but follow the same rules as used for behavioral observation. -Establish behavioral categories. -Use the frequency method, the duration method, or the interval method for obtaining numerical scores. -Employ multiple observers for at least part of the measurement process to obtain a measure of inter-rater reliability.
factorial design
is a research design that includes two or more factors.
Variance
is a statistical value that measures the size of the differences from one score to another -If the scores all have similar values, then the variance is small; - if there are big differences from one score to the next, then variance is large. -big differences between treatments are good because they provide evidence of differential treatment effects. - big differences within treatments are bad because the differences that exist inside the treatment conditions determine the variance of the scores
A-B-B1-A-BC-C
letter sequence indicates that the researcher first made a series of baseline observations, and then implemented a treatment (B) while continuing to make observations. Next, the researcher tried a modification of the treatment (perhaps treatment B was not effective), followed by withdrawal of all treatment (back to baseline). Then, the original treatment (B) was administered in combination with a new treatment (C) and finally, treatment C was administered by itself.
Amy wants to understand how creative problem-solving changes through adulthood and has been following a group of adults for almost 20 years, charting how their problem-solving skills change. This design is
longitudinal
A nonexperimental design
makes no attempt to minimize threats to validity.
A between-subjects nonexperimental or quasi-experimental design is called a _____________ design
nonequivalent groups
Calculating a Correlation Coefficient
o Consistency or strength- Correlation (correlation coefficient)- Measures and describes the relationship between two variables. The sign (+/-) indicates the direction of the relationship. The numerical value (0.0 to 1.0) indicates the strength or consistency of the relationship. The type of correlation (Pearson or Spearman) indicates the form of the relationship.
• Three common examples of nonequivalent group designs:
o Differential research design (nonexperimental) o Posttest-only nonequivalent control group design (nonexperimental) o Pretest-posttest nonequivalent control group design (quasi-experimental)
• Calculating a Correlation Coefficient
o Direction-Positive relationship- As one variable increases ► the other variable increases. As one variable decreases ► the other variable decreases. -indicated by positive values (greater than zero) -cluster around a line that slopes up to the right. Negative relationship Increases in one variable ► matches with decreases in the other variable. -indicated by negative values (less than zero) - cluster around a line that slopes down to the right
Time-related threats to internal validity
o History-A threat to internal validity from any outside event that influences the participants' scores in one treatment differently than in another treatment. o Maturation-A threat to internal validity from any physiological or psychological changes that occur in a participant during the time that research study is being conducted and that can influence the participant's scores. o Instrumentation-A threat to internal validity from changes in the measurement instrument that occur during the time a research study is being conducted. Also known as instrumental bias or instrumental decay.
Time-related threats to internal validity
o Regression toward the mean-A statistical phenomenon in which extreme scores (high or low) on a first measurement tend to be less extreme on a second measurement; considered a threat to internal validity because changes in participants' scores could be caused by regression rather than by the treatments. Also known as regression toward the mean. o Order effects-Whenever individuals participate in a series of treatment conditions and experience a series of measurements, their behavior or performance at any point in the series may be influenced by experience that occurred earlier in the sequence. Fatigue effects-progressive decline in performance as a participant works through a series of treatment conditions Practice effects-progressive improvement in performance as a participant gains experience through the series of treatment condition Carry-over effects-Changes in the scores observed in one treatment condition that are caused by the lingering aftereffects of a specific earlier treatment condition. • Contrast effect-An example of a carryover effect in which the perception of a treatment condition is influenced by its contrast with the previous treatment
• Expanding and replicating a previous study
o Replication-repeating the previous study by using the same factor or IV exactly as it was used in the earlier study. o Expansion- adding a second factor in the form of new conditions or new participant characteristics. Ascertain whether previously reported effects can be generalized to new situations / new populations.
a within-subjects nonexperimental or quasi-experimental design is called a _____________ design.
pre-post
Likert Scale
rating scale presented as a horizontal line divided into categories so that participants can circle a number or mark an X at the location corresponding to their response. -scale is presented with equal spacing between the different response choices. - idea is to simulate an interval scale of measurement, and the responses from rating scales are treated as interval measurements. the distance between agree and strongly agree is treated as a 1-point distance that is equivalent to any other 1-point difference on the scale.
• Complete counterbalancing
requires presenting the treatments in every possible sequence.
Histogram
shows a bar above each score so that the height of the bar indicates the frequency of occurrence for that particular score. The bars for adjacent scores touch each other.
Polygon
shows a point above each score so that the height of the point indicates the frequency. Straight lines connect the points, and additional straight lines are drawn down to the horizontal axis at each end to complete the figure.
• Level
simply refers to the magnitude of the participant's responses. If all of the observations within a phase indicate approximately the same magnitude, or level, of behavior, then the data have demonstrated a consistent or stable level of behavior within the phase. -concept of a stable level simply means that the data points within a phase tend to form a horizontal line on the graph.
• Inter-rater reliability
the degree of agreement between two observers who simultaneously record measurements of the behaviors -computed, either by computing a correlation between the scores for the two observers -or by computing a proportion of agreement , ranging from 1.00, perfect agreement, to 0, no agreement,
A factorial study is a purely nonexperimental design
the factors are non-manipulated or quasi-independent variables Note: the non-manipulated variables are still called factors.
• Regression
the statistical process of finding the linear equation that produces the most accurate predicted values for Y using one predictor variable (X)
Moreover, even when a relationship does exist, it is possible that another variable is actually the cause of an observed relationship. This is called the ___________problem.
third-variable
Developmental research designs
used to examine changes in behavior related to age.
• The third-variable problem
variable is controlling the two variables and is responsible for producing the observed relation.
• Multiple regression
when the process uses more than one predictor variable.
Miles is studying visual memory function in a clinical setting. He recruits individuals in the early stages of dementia, administers a test of visual memory, and then tests them again after they have been on a medication that may slow the progress of dementia for a month. This is a _______________ design.
within-subjects
• Variance
•For each score, measure the distance away from the mean. This distance is called a deviation. •Square each of the distances and compute the average of the squared distances. This is variance. •To compute the average squared distances divide the sum of the squared distances by n - 1. The variance measures the average squared distance from the mean. -the sample variance is s^2
