1. What is one disadvantage of doing research using a case study instead of using a small N study design?
a. A case study will provide less quality or detailed information about participants compared to a small N study
b. Researchers cannot publish the results of a case study for legal purposes
c. It is more likely that a case study will be subject to practice/fatigue effects compared to a small N study
d. The findings from a case should not be generalized outside of the research study
2. Researchers have measured the contents of people’s trash and the bumper stickers that people put on their cars to infer about their nature. These two examples are what type of research design?
a. event sampling
b. archival studies
c. participant observation studies
d. trace studies
3. The split-half method for estimating reliability of a survey / test involves …
a. splitting a survey/test into two smaller halves and finding the correlations between both halves
b. splitting double-barreled questions into two separate questions to see if this improves the reliability of the test.
c. giving one half of the class a test and the other half of the class a parallel form of the same test to see if there is a strong, positive correlation.
d. chopping the test in half with an axe.
4. A structured survey can be better than an unstructured survey because…
a. An unstructured survey will have lower face validity than a structured survey
b. All participants will experience a structured survey in the same way
c. A structured survey is always shorter than an unstructured survey
d. A structured survey allows a participant to control the topics that are covered
5. Compared to an A-B-A design, how is an A-B-A-B design different?
a. It leaves subjects exactly where they were when the study began.
b. It evaluates the treatment twice.
c. Participants in an A-B-A-B design are less affected by practice effects compared to an A-B-A design.
d. It withdraws the treatment twice.
6. All of the following could be used to control for subject bias, except
a. using some degree of deception
b. conducting a naturalistic observation study
c. conducting a double-blind study design
d. informing participants of the study hypothesis instead of deceiving them
7. What is content validity?
a. A measure of how well items on a test represent a variety of domains of interest (i.e. based on a theory/model)
b. A measure of whether test takers know what a test is trying to measure or not
c. A measure of how well a test can predict some future behavior (based on the correlation between two tests)
d. A measure of how well test takers perform on a test that measures a construct
8. Why would a person use reverse coding when constructing a survey?
a. To obtain “X” and “Y” values necessary for computing a correlation
b. To adjust the scores of test takers to equal the scores of other test takers
c. To make sure that some test questions are really measuring high or low levels of some characteristic about a person
d. To have a number of different scoring methods, which reduces the amount of bias that might come from a person who scores the test
9. What is an advantage of conducting a small N study compared to a large N study?
a. Collecting information from a few subjects allows researchers to focus on describing each individual in depth.
b. It is helpful in assessing the effectiveness of treatment on behavior change for specific individuals.
c. Researchers often do not need to calculate averages for participants in small N groups
(group averages can ignore individual differences)
d. All of the above
10. Studies that attempt to measure progress or development (for each participant) are…
a. Within subjects designs
b. Between subjects designs
c. quasi experimental designs ONLY
d. testing the effectiveness of a drug treatment or medication
11. Which of the following research designs compares the effectiveness of different levels of treatment (i.e. dose of medication) on the same individual?
a. Alternating treatment designs
b. Multiple baseline designs
c. A-B-A design
d. A-B design
12. Lorenz’s research on animal and human “imprinting” at young ages was an example of what kind of research?
a. Small N study
b. Case study
c. Naturalistic observation
d. Participant observation
13. I know the following is true: If you miss the exam, you will get a 0 on the test. Which of the following statements is an example of the fallacy of affirming the consequent?
a. If you do NOT get a zero on the test, you did NOT miss the exam.
b. If you did NOT get a zero on the test, you missed the exam.
c. If you got a zero on the test, you did NOT miss the exam.
d. If you got a zero on the test, you missed the exam.
14. Which of the following examples was a study that used only naturalistic observation?
a. Ebbinghaus’s (1930) memory and “forgetting” curve study
b. Fraley & Shaver’s study investigating the attachment styles of couples at an airport
c. Festinger & Carlsmith’s (1959) study investigating cognitive dissonance
d. All of the above
15. Research involving H.M. (the research participant who had his hippocampus removed to prevent seizures) is an example of what type of research design?
a. A-B design
b. Small N study
c. Operant conditioning
d. Case study
16. A researcher wants to measure the reliability of a test. They ask participants to take parallel forms of a test (i.e. both Form A and B) and see if both test scores are correlated. What is a problem with using this method to establish reliability?
a. Practice effects could cause participants to do worse on the second test form
b. You cannot correlate Form A and Form B – you must only use the test-retest method to measure reliability
c. There is an increased chance that participants can cheat using parallel form
d. If questions on Form A and B are exactly the same (just in a different order), one test form may be
harder than the other test form
17. If an IQ test is a valid measurement tool for intelligence, and a child scores 110 on this test, which of the following is also true?
a. the child should be placed in advanced classrooms
b. the child will score 110 on the IQ test every time they take the test
c. the IQ test does not necessarily measure the child’s intelligence
d. the IQ test should accurately and consistently measure IQ
18. Which of the following tests were designed to measure specific criteria regarding a person’s personality?
a. Thematic Apperception Task (TAT)
b. California Personality Index (CPI)
c. Rorschach inkblot test
d. All of the above
19. Which of the following can a linear regression measure?
a. If an independent variable can significantly predict a dependent variable
b. The rate of change for the dependent variable.
c. None of the above
d. Both A and B
20. What is criterion validity?
a. A measure of whether test takers know what a test is trying to measure or not
b. A measure of how well a test measures the construct it was designed to measure
c. A measure of how well items on a test represent a variety of domains of interest (i.e. based on a
theory/model)
d. A measure of how well a test can predict some future behavior