Deck 3: Methods for Research and Evaluation

Question 1

A test's ability to produce the same results over time is its:

A) Reliability.
B) Validity.
C) Utility.
D) Generalizability.

Answer 1

A

Question 2

Estefani and Stephania are looking at videos of bullying behaviors on playgrounds. They both look at a video of one child pushing another and code it as aggression. This illustrates:

A) Split half reliability.
B) Test-retest reliability.
C) Internal consistency.
D) Inter-rater reliability.

Answer 2

D

Question 3

When a test is as short as possible but also comprehensive it is said to have:

A) Split half reliability.
B) Test-retest reliability.
C) Internal consistency.
D) Inter-rater reliability.

Answer 3

C

Question 4

Hassan has developed a test for aggressive behavior. He finds that he only needs to calculate the even numbered questions for reliability instead of the entire test. This would indicate his test has good:

A) Split half reliability.
B) Test-retest reliability.
C) Internal consistency.
D) Inter-rater reliability.

Question 5

Logan takes the GRE and scores a combined 1,150. He retakes the test six months later and again scores a 1,150. This indicates that the test:

A) Has high content validity
B) Has high test retest reliability
C) Has high predicative validity
D) Has high internal consistency.

Question 6

Whereas ____ refers to whether a test measures what it is supposed to measure, ____ means that that the measure is consistent.

A) Reliability; validity
B) Validity; reliability
C) Utility; generalizability
D) Generalizability; utility

Question 7

If a test measures what it is supposed to measure, it is said to have:

A) Reliability.
B) Validity.
C) Utility.
D) Generalizability.

Question 8

A test of aggressive behavior includes statements such as, "When I get mad I punch people in the face." These would represent:

A) Content validity
B) Concurrent validity
C) Face validity
D) Construct validity

Question 9

A test of extraversion correlates highly with a test of sociability. This would demonstrate high:

A) Content validity.
B) Concurrent validity.
C) Face validity.
D) Construct validity.

Question 10

Dulce designs a new test of neuroticism and correlates it with existing measures like a sub-scale from the MMPI-2; she finds they correlate highly. This demonstrates high:

A) Predicative validity.
B) Concurrent validity.
C) Face validity.
D) Construct validity.

Question 11

If GRE scores are designed to predict intelligence and people who score 1,300 get all A's in graduate school, then the GRE would have high:

A) Predicative validity.
B) Concurrent validity.
C) Face validity.
D) Construct validity.

Question 12

A variable that makes it difficult to determine the effect of the treatment variable on the dependent measure is known as an:

A) Independent variable.
B) Dependent variable.
C) Confounding variable.
D) Control variable.

Question 13

Kali is in an experiment where subjects are given a drug that is supposed to make them feel less depressed. She starts to feel better even though she is in the control group. This is known as the:

A) Self-confirming bias.
B) Placebo effect.
C) Representativeness heuristic.
D) Equipoise principal.

Question 14

Esperanza is in an experiment where subjects are given a drug that is supposed to make them feel less anxious. Neither Esperanza nor the researcher know what treatment she is receiving. This is known as a(n):

A) Single-blind study.
B) Placebo effect.
C) Double-blind study.
D) Equipoise principal.

Question 15

Terrell is performing a study on the effects of benzodiazepines on anxiety. Some patients are in the control group and others in the experimental group. Only Terrell knows who is in what group. This is known as a:

A) Single-blind study.
B) Placebo effect.
C) Double-blind study.
D) Equipoise principal.

Question 16

A treatment is said to be _____ if the main variable influences the purported dependent variable; if p<.05 than the measure is said to be ______.

A) statistically significant; clinically significant
B) generalizable; valid
C) clinically significant; statistically significant
D) valid; reliable

Question 17

One of the advantages of a two-group design is that it:

A) reveals specificity treatment effects.
B) allows for long term follow up.
C) patients are motivated to participate.
D) controls for history effects.

Question 18

Research based on things like observations of behaviors is classified as:

A) Quantitative.
B) Qualitative.
C) Reliable.
D) Replicable.

Question 19

A(n) _____ seeks to determine if a particular service is needed and useful and, if so, for whom it would be best whether there is a need for it.

A) Experiment
B) Correlation
C) Program evaluation
D) Microgenetic study

Question 20

Briefly describe the constructs of reliability and validity. If you have to pick one, which would it be and why?

Question 21

Briefly define each of the following:
Reliability
Internal consistency
Test-retest reliability
Inter-rater reliability
Split-half reliability
Validity
Face validity
Content validity
Construct validity
Criterion validity
Predictive validity
Concurrent validity

Question 22

Briefly describe case studies and explain why they are used. Include both the pros and the cons of this design.

Question 23

Briefly design a study looking at different treatments for anxiety. Make sure you define and explain why you would or would not use each of the following: randomized controlled trial, control group, experimental group, placebo, single blind, and double blind techniques.

Question 24

Briefly describe the advantages and disadvantages of a two-group design versus a three-group design.