Final Exam Review; Ch 8-13, Lec 8-13 Flashcards
What kind of design is best to identify cause and effect relationships between variables?
Experimental
T or F: In experimental designs, cause and effect relationships are identified by establishing covariation, temporal precedence, and the elimination or control of extraneous variables
T
What is this: changes in one variable are associated with changes in another variable
Covariation
What is this: changes in the suspected cause (treatment) occur before changes in the effect (outcome)
Temporal precedence
What is this: factors other than the intended treatment that might change the outcome measure
Extraneous variables
What is this: the degree to which we can rule out other possible causal explanations for the relationship between the independent and dependent variables
Internal validity
What is this: does the study parallel everyday situations in the real world?
Mundane realism
What is this: how engaged are participants so that their reactions are natural in response to the manipulation
Experimental realism
What is the difference between a control and experimental group?
Control receives no or different level of treatment and is the comparison group; receives treatment
What is experimental control?
Ability to keep everything between groups the same except for the one element we want to test in an experiment
What is the assumption of independence?
Each participant represents a unique and individual data point
What kind of research design is this: researcher creates a set of two participants who are highly similar on a key trait and randomly assigns individuals in the pair to different groups
Matched pair design
What is required in a matched pair design?
Controlled variable be measured in advance
When is a t-test for independent means used?
One independent variable with two levels/conditions
T or F: The null hypothesis is when there is no statistically significant effect of the independent variable
T
What is a multigroup design?
3 or more levels of the independent variable
How many levels are needed to identify a linear vs. non linear relationship?
2 levels vs. at least 3
What is an empty control group?
Participants complete dependent measure without receiving treatment
What is a placebo group?
Participants falsely believed they are receiving treatment
T or F: hypothesis guessing is when a participant in a study actively tries to identify purpose of the research
T
What is methodological pluralism?
Use of multiple methods or strategies to answer the research question
What is power?
A study’s ability to find differences between groups when there is a real difference; the probability that a study will yield significant results
What is this: variable that the researcher unintentionally varies along with the manipulation
Confound
What is a one way analysis of variance (one way ANOVA)?
Statistical test that determines whether responses from the different conditions are essentially the same or whether the responses from at least one of the conditions differ from the others
What is a limit of the one way ANOVA?
Does not tell us where the action is in terms of which specific conditions differ from other conditions
What do exploratory analyses investigate?
Potential differences that were not anticipated or predicted prior to conducting the study
What kind of test is this: examine all possible combinations of conditions in a way that statistically accounts for the fact that not all of them were predicted ahead of time
Post hoc tests
T or F: in planned contrast tests, examines the comparisons between groups that were predicted ahead of time
T
What is a benefit of planned contrast tests?
Allows the comparison of combined conditions to other conditions in the study
What is a chi square test of independence?
Both variable categorical. Examines if the distribution of participants across categories is different from what would happen if there was no difference amongst the groups
What kind of design is this: measure the depedent variable before and after exposing participants to a treatment or intervention
Pretest-posttest (within subjects)
What kind of design is this: expose participants to each level of the independent variable and measuring each on the dependent variable after each level
Repeated-measures (within subjects)
What are 2 advantages of within subjects designs?
Statistical power (do not have to worry about individual differences between groups; increases likelihood of correctly rejecting the null hypothesis when it’s false) and efficiency (fewer participants needed compared for a between subjects design)
What is this associated with: are changes in the DV due to treatment?
Internal validity
What are 4 threats to validity in pretest-posttest’s?
Maturation (changes occur spontaneously over time), attrition/mortality (differential dropping out of participants), history (external event that may influence participant behavior), testing (practice with dependent measure may affect scores on second test)
What are solutions for each of the 4 threats to validity in pretest-posttest’s?
Use control group, remove participants from pretest data, control group, comparison group that shows less change
What is the practice vs. fatigue effect (sequence/order effects)?
Changes in responses due to increased experience with measurement instrument; deterioration in measurements due to participants becoming tired or less attentive over the course of the study
What happens in the randomizing the order of levels as a control for order effect?
Vary the sequence of experimental conditions so that they are not always in the same order
What happens in counterbalancing as a control for order effects?
All potential treatment sequences are used in a within subjects design to first identify all possible sequences and then randomly assigned to participants
What happens in the latin square design as a control for order effects? When is this used?
Counterbalancing strategy where each experimental condition appears at every position in the sequence order equally often (makes order sequence its own IV); large repeated measures designs
What is this: the desire to see what one is not supposed to see
Voyeurism
What is the instrumentation problem?
In terms of threats to internal validity, change in how a variable is measured or administered during the course of a study
What is the carryover effect?
Exposure to earlier experimental conditions influencing responses to subsequent conditions
What is the sensitization effect?
Continued exposure to experimental conditions in a within subjects study increasing the likelihood of hypothesis guessing
What is schadenfreude?
Feelings of pleasure a person experiences after learning about or observing the misfortunes of others
How do factorial designs benefit researchers?
Allows them to look at the effect of more than one variable at a time
What does the simplest version of a factorial design consist of?
2 IV’s at each level, 2 IV’s per level, 4 conditions in the study (2x2 factorial design)
What do the numbers tell us in factorial designs?
Number of IV’s
What is an additive effect?
When the combined effect is the sum of the separate effects
When does an interaction occur in a factorial design?
When the effect of an IV changes at different levels of another IV
What kind of interaction in a factorial design is this: IV has opposing effects on the DV at the different levels of the other IV
Crossover (disordinal)
What kind of interaction in a factorial design is this: IV has a larger effect on the DV at one level of the other IV than at another level of that IV
Ordinal
What kind of effect in a factorial design is this: The combined effect of two variables is greater than the effects of each variable
Synergistic
What kind of effect in a factorial design is this: The combined effect of two variables is less than the effects of each variable
Suppression
What is the difference between cell vs. marginal means?
Average for whole cell vs. average for individual item in the cell
What is a hybrid design?
Any factorial design that has at least one quasi-IV
What is the main effect hypotheses?
Prediction that focuses on the effect of one IV in the DV at a time, ignores other IVs
What is the interaction effect hypothesis?
Prediction about how the levels of one IV will combine with another IV to impact the DV in a way that extends beyond the sum of the two separate main effects
What does vignette mean?
A description of a hypothetical situation, event, or scenario to which participants react
What is a two way analysis of variance (two way ANOVA/factorial ANOVA)?
Statistical test that allows us to simultaneously test how two separate nominal or categorical IVs influence the DV, and how those IVs interact to influence the DV
What is a mixed design?
Factorial design that includes at least one within subjects IV and at least one between subjects IV
What is a single subject design/single case experimental/single n design?
Type of within subjects design using one participant/one group to assess changes within that individual or group
What is an A-B design?
Single subject design in which researchers take a baseline measurement (A), then introduce the intervention, and then measure the same variable again (B)
What is an A-B-A design?
Single subject design in which researchers establish a baseline (A), introduce the intervention and measure the same variable again (B), then remove the intervention and take another measurement (A)
What is an A-B-A-B design?
Single subject design in which researchers establish a baseline (A), introduce the intervention (B), remove the intervention (A), and then reintroduce the intervention (B), measuring the DV each time
What kind of group is this: Comparison group often used in clinical research in which an already established treatment is administered for comparison to experimental treatment
Treatment as usual group
What kind of group is this: Control group often used in clinical research where participants in this group do not receive treatment or intervention until after the completion of the study
Waiting list control group
What is the experimenter-expectancy effect/expectancy bias/experimenter effect?
When bias causes a researcher to unconsciously influence the participants of an experiment
What kind of procedure is this: Both participants and the administrators of treatment or blind to the types of treatment being provided
Double blind
What kind of procedure is this: Participants are blind to the types of treatment being provided, administrators are not
Single blind
What does locus of control mean?
Generalized expectancies for internal versus external control of reinforcement
What is a program evaluation? What is it like?
Using the scientific method to assess whether an organized activity is achieving its intended objectives; progress check
What kind of evaluation is this: Assessment of features of a program that are most valuable and who they benefit the most
Needs
What kind of evaluation is this: Assessment of general program operation, including who the program serves and how the program delivers services to that population
Process
What kind of evaluation is this: Assessment of whether a program effectively produces outcomes that are consistent with stated objectives or goals
Outcomes
What are the 3 phases of the program evaluation process?
Planning, execution, communication
What does the planning phase in the program evaluation process consist of?
ID who uses and who benefits from the evaluation, describe program missions, gals, nature of program and services, and who it serves, clarify evaluation goal and what it hopes to accomplish and how to use the results, create evaluation plan
What does the execution phase in the program evaluation process consist of?
Gather data via interviews, focus groups, and surveys, and analyze data by using appropriate stats to summarize info collected and put into a form that will be useful for the program
What does the communication phase in the program evaluation process consist of?
Evaluate findings to determine what are the supported conclusions, interpret findings and how they relate to the programs goals and ID strong and weak points and make suggestions for how the data should inform potential modifications, communicate findings to stakeholders in layman terms
What is a focus group and what is an advantage and a disadvantage?
6-12 individuals to discuss a topic; high volume insightful content using participants own words in a quick and efficient manner; inability to generalize to other populations
What is a single term indicator?
One item or question used to measure a variable
What is a single sample t-test?
Statistic to evaluate whether a sample mean statistically differs from a specific value
