ISS 305
Exam 2 Practice Questions
& Answers.
1) Reliability depends on how well has been controlled, while validity depends on how well
has been controlled.
a. noise ; bias
b. random error ; systematic error
c. bias ; noise
d. systematic error ; random error
e. Both A and B are correct answers.
f. Both C and D are correct answers.
2) Random error
a. tends to increase across repeated measures.
b. tends to increase over a large number of observations.
c. distorts measurements in a single direction.
d. None of the answers above are correct.
3) An experimenter uses the bogus pipeline because he or she wants to:
a. make the participant feel more comfortable.
b. decrease reactance.
c. increase the likelihood that the participant will report their true attitudes.
d. help the participant access heuristics.
4) Intelligence is not observed directly. Rather, its existence is inferred from certain behaviors that are assumed to
represent intelligence. Thus, intelligence is a(n)
a. conceptual variable
b. operational definition.
c. variable that means that same thing to everyone.
d. fun thing to talk about.
5) Which of the following is possible?
a. A measure has high reliability and high validity.
b. A measure has low reliability and low validity.
c. A measure has high reliability and low validity.
d. A measure has low reliability and high validity.
e. A, B, and C are all possible. D is impossible.
f. A, B, C, and D are all impossible.
6) We are developing a new questionnaire to assess worry. We find that the scores on our new measure correlate
highly with an existing measure of worry, but do not correlate at all with a measure of intelligence. Thus we can
say that our measure has good:
a. concurrent and predictive validity.
b. convergent and discriminant validity.
c. face and content validity.
d. All of the above answers are correct.
7) Your friend did face-to-face interviews with a large group of people (300+) and found that none of them had ever
picked their nose. Why should you question their conclusion that "no one picks their nose"?
a. The participants may have been responding in a socially-desirable way.
b. Actually, the large sample makes this pretty solid evidence that people don't pick their noses.
c. The results indicate a moderation response biases.
d. The results indicate an acquiescence response bias.
, 8) Dirk is very short and skinny. However, every single time he steps on his bathroom scale it reports that he weighs
900 pounds. Dirk’s bathroom scale has a level of reliability and a level of validity.
a. high ; high
b. high ; low
c. low ; high
d. low ; low
9) Responding in a socially desirable way, instead of honestly, undermines that of a measure.
a. reliability
b. symmetry
c. random error
d. none of the answers presented are correct.
10) Ben decides to measure racial tensions at MSU by asking students to rate the degree to which they agree with the
following statement on a scale from 1-5 (1=strongly agree and 5=strongly disagree): 'I dislike students who are
not the same race as me.' Student responses lead him to conclude that there is practically no racial prejudice at
MSU. But suppose that racists choose not to admit their racist attitudes (for example, to avoid looking politically
incorrect). This would create a problem of:
a. low level of measurement.
b. low reliability of measurement.
c. low validity of measurement.
d. low empiricism.
11) In a study of ice cream taste preferences, participants are asked to place the following flavors from most to least
favorite: vanilla, chocolate, pistachio, and butterscotch. The measurement scale used in this study is best
described as:
a. nominal
b. ordinal
c. interval
d. ratio
12) At football practice, Coach Dantonio divides the team into two groups: offense (A) and defense (B). The scale
Coach Dantonio uses to divide his team is called a(n) scale.
a. nominal
b. ordinal
c. interval
d. ratio
13) Geoff asks the students in his 9th grade classroom to test the pH levels of the soil in the playground. The average
pH level of the students’ measurements were both higher and lower than the measurement made by experts from
the University extension service. This strongly suggests in the students’ measurements.
a. negative error
b. systematic error
c. random error
d. high validity
14) James took an oral examination in history that was scored by 3 professors. All 3 professors separately gave James
a high passing grade on the oral exam. This indicates a level of for the oral exam measure.
a. low ; interjudge reliability
b. low ; predictive validity
c. low ; test-restest reliability
d. high ; interjudge reliability
Exam 2 Practice Questions
& Answers.
1) Reliability depends on how well has been controlled, while validity depends on how well
has been controlled.
a. noise ; bias
b. random error ; systematic error
c. bias ; noise
d. systematic error ; random error
e. Both A and B are correct answers.
f. Both C and D are correct answers.
2) Random error
a. tends to increase across repeated measures.
b. tends to increase over a large number of observations.
c. distorts measurements in a single direction.
d. None of the answers above are correct.
3) An experimenter uses the bogus pipeline because he or she wants to:
a. make the participant feel more comfortable.
b. decrease reactance.
c. increase the likelihood that the participant will report their true attitudes.
d. help the participant access heuristics.
4) Intelligence is not observed directly. Rather, its existence is inferred from certain behaviors that are assumed to
represent intelligence. Thus, intelligence is a(n)
a. conceptual variable
b. operational definition.
c. variable that means that same thing to everyone.
d. fun thing to talk about.
5) Which of the following is possible?
a. A measure has high reliability and high validity.
b. A measure has low reliability and low validity.
c. A measure has high reliability and low validity.
d. A measure has low reliability and high validity.
e. A, B, and C are all possible. D is impossible.
f. A, B, C, and D are all impossible.
6) We are developing a new questionnaire to assess worry. We find that the scores on our new measure correlate
highly with an existing measure of worry, but do not correlate at all with a measure of intelligence. Thus we can
say that our measure has good:
a. concurrent and predictive validity.
b. convergent and discriminant validity.
c. face and content validity.
d. All of the above answers are correct.
7) Your friend did face-to-face interviews with a large group of people (300+) and found that none of them had ever
picked their nose. Why should you question their conclusion that "no one picks their nose"?
a. The participants may have been responding in a socially-desirable way.
b. Actually, the large sample makes this pretty solid evidence that people don't pick their noses.
c. The results indicate a moderation response biases.
d. The results indicate an acquiescence response bias.
, 8) Dirk is very short and skinny. However, every single time he steps on his bathroom scale it reports that he weighs
900 pounds. Dirk’s bathroom scale has a level of reliability and a level of validity.
a. high ; high
b. high ; low
c. low ; high
d. low ; low
9) Responding in a socially desirable way, instead of honestly, undermines that of a measure.
a. reliability
b. symmetry
c. random error
d. none of the answers presented are correct.
10) Ben decides to measure racial tensions at MSU by asking students to rate the degree to which they agree with the
following statement on a scale from 1-5 (1=strongly agree and 5=strongly disagree): 'I dislike students who are
not the same race as me.' Student responses lead him to conclude that there is practically no racial prejudice at
MSU. But suppose that racists choose not to admit their racist attitudes (for example, to avoid looking politically
incorrect). This would create a problem of:
a. low level of measurement.
b. low reliability of measurement.
c. low validity of measurement.
d. low empiricism.
11) In a study of ice cream taste preferences, participants are asked to place the following flavors from most to least
favorite: vanilla, chocolate, pistachio, and butterscotch. The measurement scale used in this study is best
described as:
a. nominal
b. ordinal
c. interval
d. ratio
12) At football practice, Coach Dantonio divides the team into two groups: offense (A) and defense (B). The scale
Coach Dantonio uses to divide his team is called a(n) scale.
a. nominal
b. ordinal
c. interval
d. ratio
13) Geoff asks the students in his 9th grade classroom to test the pH levels of the soil in the playground. The average
pH level of the students’ measurements were both higher and lower than the measurement made by experts from
the University extension service. This strongly suggests in the students’ measurements.
a. negative error
b. systematic error
c. random error
d. high validity
14) James took an oral examination in history that was scored by 3 professors. All 3 professors separately gave James
a high passing grade on the oral exam. This indicates a level of for the oral exam measure.
a. low ; interjudge reliability
b. low ; predictive validity
c. low ; test-restest reliability
d. high ; interjudge reliability
