PSY 500 Notes
Module 3
What is the best way to describe the relationship between the independent variable and the dependent variable in an experiment or quasi-experiment? (Use the concept of change and/or manipulation in your description.)
What, if any, is the difference between an extraneous variable and a confounding variable?
What is a control and what is its purpose?
Why does random assignment help to minimize the impact of potential extraneous or confounding variables on the study outcomes? In other words, what impact does random assignment have on random error and systematic error?
Does random selection help to minimize the impact of potential extraneous or confounding variables on the study outcomes in the same way that random assignment helps? Explain.
What are some sampling techniques that help to promote group equivalence? What are the disadvantages of these techniques?
What should you look for in a report of a study that did not use random assignment?
What does it mean when we say that confounds provide for alternative interpretations for the outcomes of study (also referred to as alternative hypotheses)? Can you give an example?
What is internal validity? What is the main goal of internal validity?
What is a lurking variable? What does it mean for a lurking variable to create a spurious relationship between two other variables?
Are mediating and moderating variables considered to be lurking/confounding variables? Why or why not?
Suppose the relationship between trait resilience and IQ is known to be strong (as IQ increases, so does trait resilience). The relationship between mortality risk and IQ is also known to be strong, but inverse (as IQ increases, risk of mortality decreases; or high IQ predicts a longer life). Give this information, are you able to draw any conclusions about the relationship between resilience and mortality risk? Explain.
What are the sources of lurking variables within each category: non-comparable groups, endogenous changes in participants, treatment misidentification, contamination, and history?
What are biosocial and psychosocial experimenter effects and demand characteristics?
What is a solution for each type of threat to internal validity that would help minimize the influence on study outcomes? In other words, what are the controls?
What is the cone of validity? What does the cone of validity indicate about the difference between a field experiment and a single lab experiment in relation to internal and external validity? If they are both experimental designs, why do they differ in placement on the cone?
Which is better at protecting internal validity, experimental designs or quasi-experimental designs? Why? Which is better at protecting external validity? Why?
What is the difference between sampling bias and selection bias, and how would high levels of each influence the results of a study?
Why are descriptive research and one-group, posttest-only designs categorized as pre-experimental?
What is a quasi-experimental design, and why is it used by researchers?
What is a randomized block design and why is it used by researchers?
What are the necessary conditions for a design to be considered a true experiment?
Is a single-case design (aka single-subject design) a true experimental design? Explain. Also, what are the advantages and disadvantages of this type of design?
What is a Solomon four-group design, and why is it used by researchers?
What is a crossover design and why is it used by researchers?
What is a factorial design, and why is it used by researchers?
What is the difference between a within-subjects design and a between-subjects design? What are the advantages and disadvantages of each?
Which is better at protecting internal validity, experimental designs or quasi-experimental designs? Why? Which is better at protecting external validity? Why?
What do we mean by the term replicability? Which types of designs are easiest to replicate? Why?
Module 4
What is a manipulation check? Why do researchers conduct manipulation checks during and/or after an experiment?
What are the four major types of validity for a research study? Note any sub-types noted. How is each type of validity evaluated?
What is measurement validity? What are the different types of measurement validity and how is each established?
What is measurement reliability? What are the different types of measurement reliability and how can threats to each be minimized? How does reliability relate to variance in the data?
What are some common sources for loss of reliability? Explain each.
What are the successive measurements, single measurement points, and simultaneous measurements used for estimating reliability? What are the advantages and disadvantages of each method?
Can a measure be valid but not reliable? Can a measure be reliable but not valid? Explain.
Should researchers use self-report scales to measure the dependent variable(s) in a study? Why or why not?
Why is a measure of Fahrenheit temperature considered to be at the interval level of measurement and not the ratio level of measurement?
Are IQs measured at the interval level or the ordinal level? Explain.
Why do some researchers suggest that data from Likert scales can only be used to rank order respondents, as opposed to using the data to determine how much more favorable one respondent is to another respondent?
Should Likert scales include a midpoint? Explain. What are some other important considerations for constructing a Likert scale?
Why should researchers avoid forced-choice items?
What is interrater reliability? What are some factors that influence interrater reliability?
When data is gathered through the use of raters/judges, why is it better to use multiple raters instead of just one?
If raters are used to categorize the levels of the independent variable (i.e., classify participants into groups), what are the ramifications for the study if interrater reliability is low?
How might the rater’s perception of the participant influence (consciously or unconsciously) the rating given?
