Research Methods for the Behavioral Sciences 5th Edition by Charles Stangor – Test Bank

Complete Test Bank With Answers

 

 

Sample Questions Posted Below

 

CHAPTER 5

Reliability and Validity

LEARNING OBJECTIVES

1. Define random and systematic error and to understand how they influence measurement.

2. Define reliability and understand why measures must be reliable.

3. Understand how test-retest and alternate forms reliability are measured.

4. Determine how split-half reliability and coefficient alpha are used to assess the internal consistency of a

measured variable.

5. Understand interrater reliability.

6. Understand face and content validity.

7. Understand how convergent and discriminant validity are used to assess the construct validity of a measured

variable.

8. Define criterion validity.

9. Determine what methods can be used to increase the reliability and validity of a self-report measure.

10. Understand the similarities and differences between reliability and construct validity.

ESSAY QUESTIONS

1. What is meant by the reliability of a measure? Describe three different ways of measuring reliability and

indicate when each would be most appropriate to use.

2. What is meant by the construct validity of a measure? Describe three different ways of measuring validity.

What is the difference between reliability and validity?

3. What is the internal consistency approach to measuring reliability? When would it be appropriate to use the

internal consistency approach to assessing reliability rather than the test-retest or the alternative forms

approach? What statistic is used to assess reliability when using the internal consistency approach, and

what does that statistic conceptually represent?

4. What are retesting effects and what difficulties can they cause in research?

5. Define face validity, content validity, and construct validity. Be sure to discuss the two subcomponents of

construct validity. Which of the three approaches is most objective, and why? Is it possible to have a

measure that is construct valid, but not face valid?37 Chapter 5: Reliability and Validity

Ans: a

Page: 89

Type: C

LO: 1

2. Ans: a

Page: 91

Type: F

LO: 2

3. MULTIPLE-CHOICE QUESTIONS

Ans: a

1. Which of the following is true about the difference between random and

Page: 89

systematic error?

Type: F

a. Random error is self-canceling, whereas systematic error tends to

LO: 1

increase or decrease the scores on the measured variable.

b. Random error tends to increase or decrease the scores on the

dependent variable, whereas systematic error is self-canceling.

c. d. Both random error and systematic error are self-canceling.

Because systematic error is self-canceling, it is less problematic in

research than is random error.

Changes in a person’s current mood, a misreading or misunderstanding of

the question, and measuring individuals on different days or in different

places are all likely to contribute to

a. random error.

b. systematic error.

c. reliable error.

d. operational error.

The reliability of a test refers to the extent that the test is free from

a. random error.

b. measurement bias.

c. systematic error.

d. individual traits.

Errors in recording the scores on a test that occur because the keypuncher is

not paying attention are likely to produce

a. spurious relationships.

b. low face validity.

c. random error.

d. systematic error.

A measured variable that contains a large proportion of random error is said

to be

a. unreliable.

b. invalid.

c. a state variable.

d. a trait variable.

The Graduate Record Exam (GRE) uses which approach to assess

reliability?

a. Interrater

b. Equivalent forms

c. Item to total

d. Unexpected item

Donna is in a two-part experiment. She completed a self-esteem measure

one week ago and is now taking the same measure again. Which of the

following problems may arise from this process?

a. Systematic error phenomenon

b. Violation of face validity

c. Equivalent form effects

d. Retesting effects

Ans: c

Page: 89

Type: F

LO: 1

4. Ans: a

Page: 91

Type: F

LO: 2

5. Ans: b

Page: 92

Type: C

LO: 5

6. Ans: d

Page: 92

Type: A

LO: 3

7. Ans: b

Page: 93

Type: F

LO: 1

Ans: a

Page: 91

Type: F

LO: 1

Ans: c

Page: 94

Type: F

LO: 4

Ans: a

Page: 95

Type: C

LO: 4

Ans: a

Page: 94

Type: F

LO: 4

Ans: a

Page: 94

Type: F

LO: 4

Ans: c

Page: 95

Type: F

LO: 2

Chapter 5: Reliability and Validity 38

8. 9. 10. 11. 12. 13. If it is found that people’s self-esteem changes quickly—for instance, from

day to day—then self-esteem should be considered to be

a. a trait variable.

b. a state variable.

c. an unreliable variable.

d. an invalid variable.

Which of the following equations represents the relationship between true

score, actual score, and reliability?

a. b. c. d. Reliability equals true score divided by actual score.

Reliability equals true score plus actual score.

Reliability equals actual score divided by true score.

Reliability equals actual score minus true score.

Cronbach’s coefficient alpha is a measure of which of the following?

a. b. c. d. The average validity of an item

The correlation between one item and the total scale score

The average correlation among the items

The face validity of a scale

A researcher is developing a Likert scale to measure the self-esteem of a

group of college students. He considers self-esteem to be a state, in the

sense that it will change from day to day based on a person’s experiences.

Which of the following forms of reliability should he use to assess self-

esteem?

a. Internal consistency

b. Interrater

c. Test-retest

d. Equivalent forms

Cronbach’s coefficient alpha is a measure of which of the following?

a. The internal consistency of a scale

b. Test-retest reliability

c. Interrater reliability

d. Construct reliability

Which of the following two techniques can be used to assess the internal

consistency of a scale?

a. Coefficient alpha, split-half reliability

b. Coefficient alpha, test-retest reliability

c. Test-retest reliability, equivalent forms reliability

d. Test-retest reliability, split-half reliability

14. Kappa is used

a. b. c. d. to test the construct validity of a measure.

to test the criterion validity of a measure.

to compute the reliability of a set of nominal variables.

to eliminate items from a Likert scale.39 Chapter 5: Reliability and Validity

Ans: b

Page: 95

Type: C

LO: 5

15. Ans: a

Page: 95

Type: C

LO: 1

16. Ans: a

Page: 95-96

Type: C

LO: 6

17. Ans: b

Page: 95-96

Type: A

LO: 1,6

18. Ans: a

Page: 97

Type: C

LO: 6

19. Ans: d

Page: 97

Type: C

LO: 7

20. A form of reliability that is used to assess the consistency of judgment when

more than one person has observed a set of events is known as

a. judgment reliability.

b. interrater reliability.

c. construct reliability.

d. internal reliability.

Which of the following statistics would be used to assess the reliability of a

set of raters who used a nominal variable to code behavior?

a. Kappa

b. Coefficient alpha

c. Pearson R

d. The reliability statistic

Consider the following item that might appear on a Likert scale: “I normally

do not get along well with other people.” Such an item has high

__________ validity, but may not have __________ validity because

respondents may not answer it honestly.

a. face; construct

b. construct; face

c. face; criterion

d. construct; criterion

A researcher has developed a new test of “interpersonal skills.” It consists

of measuring a person’s shoe size. The test shows a test-retest reliability

of .85. It appears that this test has __________

and

.

___________

a. b. c. d. high reliability; high face validity

high reliability; low face validity

low reliability; high face validity

low reliability; low face validity

Consider a researcher who developed a test of driving skills that involved

measuring the ability to effectively shift gears in a manual transmission car.

One might criticize this test for having low

a. content validity.

b. criterion validity.

c. predictive validity.

d. discriminant validity.

A researcher has found that his new measure designed to assess the

conceptual variable of “exoticism” correlates about +.85 with an existing

measure designed to assess “unusualness.” The researcher needs to worry

about the

of his measure.

__________

a. random error

b. measurement bias

c. face validity

d. discriminant validityAns: c

Page: 9497

Type: A

LO: 6

Ans: a

Page: 97

Type: F

LO: 7

Ans: d

Page: 97

Type: C

LO: 6

Ans: a

Page: 97

Type: C

LO: 7

Ans: b

Page: 98

Type: F

LO: 7

Ans: a

Page: 99

Type: F

LO: 1

Chapter 5: Reliability and Validity 40

21. The students in Dr. Miller’s class are complaining that, although the exam

was supposed to cover chapters 1 through 5, the test only covered chapters

1 and 2. Why are the students upset?

a. The test isn’t reliable.

b. c. d. The test doesn’t have face validity.

The test doesn’t have content validity.

The test has incomplete validity.

22. Discriminant validity refers to

a. the extent to which a measured variable does not correlate with other

variables designed to measure different conceptual variables.

b. the extent to which a measured variable correlates with other

measured variables designed to assess different conceptual variables.

c. the extent to which a measured variable correlates with another

measured variable over time.

d. the extent to which a measured variable discriminates against other

measured variables.

23. 24. 25. 26. Of the following, which is the LEAST objective measure of construct

validity?

a. Convergent validity

b. Discriminant validity

c. Criterion validity

d. Content validity

Stanley developed a measure of hopefulness that correlates about -.90 with

a measure of despair. Stanley should now worry about the __________ of

his new measure.

a. discriminant validity

b. face validity

c. content validity

d. predictive validity

In general, when a measure has good convergent and discriminant validity

a. the correlations that measure convergent validity will be about r = 1.0

and correlations that assess discriminant validity will be about r =

0.00.

b. the correlations will not approach r = 1.0 or r = 0.00, due to random

error and the fact that many different conceptual variables are likely

to be at least somewhat related to each other,.

c. it will not be possible to differentiate the size of the correlations that

represent convergent validity from the size of the correlations that

represent discriminant validity.

d. the concurrent validity of the relationships will be greater than the

criterion validity of the relationships.

The nomological net refers to

a. b. c. the correlations among many different measured variables.

the Pearson correlation between two measured variables.

the correlation between a conceptual variable and a measured

variable.

d. the Pearson correlation between two conceptual variables.41 Chapter 5: Reliability and Validity

Ans: a

Page: 99

Type: A

LO: 9

27. Ans: b

Page: 99

Type: F

LO: 2

28. Ans: a

Page: 100

Type: F

LO: 2

29. Ans: a

Page: 102

Type: C

LO: 10

30. Ans: a

Page: 93

Type: F

LO: 2

31. Ans: c

Page: 102

Type: A

LO: 4

32. Ans: a

Page: 99-100

Type: A

LO: 6,7,8

33. A researcher who used a self-report measure of job interest to predict

performance on a managerial task would be interested in the _____

self-report measure.

a. predictive validity

b. construct validity

c. content validity

d. face validity

of her

The nomological net refers to

a. b. c. d. the reliability of a measure.

the correlations among variables that measure different constructs.

the content validity of a measure.

the network of reliabilities among conceptual variables.

In order to better understand how individuals react to a questionnaire before

using the questionnaire in a research project, the researcher may wish to

a. pilot test.

b. compute coefficient alpha.

c. compute kappa.

d. delete all distractor items from the scale.

Which of the following is a correct statement?

a. b. c. d. A scale must be reliable in order to have construct validity.

A scale must have construct validity in order to be reliable.

A scale must have face validity in order to be reliable.

A scale must be reliable in order to have face validity.

A semantic differential scale that contains 15 percent random error would

be considered

a. reliable.

b. unreliable.

c. valid.

d. invalid.

A scientist is interested in developing a scale to measure people’s mood

states. Which of the following forms of validity is likely to be most

appropriate?

a. Test-retest

b. Equivalent forms

c. Internal consistency

d. Content reliability

Which of the following statements is true?

a. A scientist who is studying construct validity will be more concerned

about what conceptual variable is actually being measured than will a

scientist who is concerned with criterion validity.

b. A scientist who is studying criterion validity will be more concerned

with the conceptual variable being measured than will a scientist who

is concerned with construct validity.

c. Construct validity is normally used to make predictions about a

behavior that will occur in the future.

d. Criterion validity can be considered to be another form of face

validity.Chapter 5: Reliability and Validity 42

Ans: d

Page: 90

Type: F

LO: 1

Ans: b

Page: 92

Type: A

LO: 3

Ans: c

Page: 99

Type: A

LO: 2

Ans: a

Page: 101-102

Type: C

LO: 10

Ans: c

Page: 100-101

Type: C

LO: 9

Ans: c

Page: 94

Type: C

LO: 4

Ans: c

Page: 97

Type: C

LO: 6

34. 35. 36. 37. 38. 39. 40. Which of the following is an example of systematic error?

a. b. c. d. The participant misreads the question.

The experimenter misprints the question.

The participant forgets to answer a question.

The participant displays socially desirable responding.

Andrea is given a questionnaire concerning her shopping habits. Two

weeks later, she is given a similar questionnaire that also assesses shopping

habits, but which contains different questions. The researcher will likely

assess which of the following?

a. interrater reliability

b. equivalent-forms reliability

c. face validity

d. construct validity

A test designed to measure baseball performance skills would be said to

have high predictive validity if a person who scores low on the test also

a. b. c. d. scores low on a test measuring basketball performance.

scores high on a test measuring basketball performance.

has a poor batting average over the baseball season.

scores high on the same test given two weeks later.

Reliability is used to assess _____________, whereas validity is used to

assess _____________.

a. b. c. d. the consistency of a measure; the accuracy of a measure

the accuracy of a measure; the consistency of a measure

the generalizability of a measure; the reactance of a measure

test reactance of a measure; the generalizability of a measure

Which of the following would be likely to improve the reliability and

validity of a measure?

a. b. c. d. Using only one measure to assess the conceptual variable

Reducing the number of questions on the test

Using pilot testing to select good questions

Decreasing the variability of measures

If the average correlation among the items on an anxiety scale is r = .95, we

can say that the scale has

a. high content validity.

b. low internal consistency.

c. high internal consistency.

d. high construct validity.

A measure of schizophrenia that measures only elements of auditory

hallucinations, but not other symptoms of schizophrenia, would be said to

have

a. low reliability.

b. high convergent validity.

c. low content validity.

d. low face validity.43 Chapter 5: Reliability and Validity

Ans: d

Page: 98-99

Type: F

LO: 10

41. Ans: b

Page: 92-93

Type: F

LO: 2

42. Ans: b

Page: 94

Type: F

LO: 2

43. Ans: c

Page: 103-104

Type: C

LO:

44.. Ans: b

Page: 103-104

Type: C

LO:

45. The major advantage of assessing similar conceptual relationships in many

different studies is that

a. b. c. d. it reduces the need for the nomological net.

random assignment is less important.

a larger p-value can be used.

the greater number of tested and confirmed predicted relationships,

the greater the construct validity of the relationships.

Individual difference variables that are expected to vary over a period of

time are called ________, while variables that are not expected to vary over

time are called _________.

a. measured variables; conceptual variables

b. states; traits

c. moving variables; stable variables

d. traits; states

If the average correlation among the items on a scale of self-esteem is r

= .15, we can say that the scale has

a. high content validity.

b. low internal consistency.

c. high internal consistency.

d. high construct validity.

Hillyer and Joynes (2009) created a new measure of locomotion in rats.

Which of the following approaches did they use to determine the reliability

of the new measure.

a. Coefficient Alpha.

b. Split half reliability

c. Inter-rater reliability

d. Test-retest reliability

In the study by Hillkyer and Joynes (1995) on locomotion in rats, the

researchers tested for productive validity by correlating an existing

measures (the BBB) and a new measure (the HUK) with a physiological

assessment of mobility. Which of the following was found?

a. b. c. d. The new measure was more sophisticated.

The new measure was better able to predict mobility.

The HiJK correlated negatively with the existing measure.

The HiJK was not reliable.