Question 1

Defining or explaining a psychological construct is referred to as ______.
A) construct validity
B) research that bears out a theory's predictions
C) calculating convergent validity
D) construct explication

Accepted Answer

Defining or explaining a psychological construct is referred to as construct explication.

Question 2

Which one of the following coefficients is NOT found in a multitrait-multimethod correlation matrix?
A) reliability coefficient
B) correlation coefficient between the test and a criterion
C) convergent coefficient
D) discriminant coefficient

Accepted Answer

The multitrait-multimethod (MTMM) matrix is designed to assess the validity of constructs by examining the relationships between different traits and methods. It includes reliability coefficients (reflecting the consistency of a measure), convergent coefficients (indicating the degree to which two measures of the same trait correlate), and discriminant coefficients (showing the degree to which measures of different traits diverge). However, it does not specifically include correlation coefficients between the test and a criterion, as these are related to criterion validity, not the internal structure assessed by the MTMM matrix.

Question 3

In 1954, the American Psychological Association (APA) published recommendations that suggested a new method for establishing validity in which the researcher provides evidence that the test measures behavior predicted by a psychological theory. What did the APA call this evidence?
A) construct validity
B) factor analysis
C) multitrait, multimethod analysis
D) generalizability

Accepted Answer

The APA called the evidence supporting the idea that a test measures behavior predicted by a psychological theory "construct validity."

Question 4

When a researcher chooses three constructs that are unrelated in theory and three types of tests such as objective, projective, and a peer rating to measure each of the constructs, she is conducting a ______.
A) multitrait-multimethod design
B) content validation study
C) generalizability study
D) factor analysis

Accepted Answer

The researcher is conducting a multitrait-multimethod design, which involves measuring several different traits using multiple methods to ensure the validity of the measures.

Question 5

When an underlying theory explains the relation between a predictor and a criterion based on a psychological theory, there is ______.
A) concurrent evidence of validity
B) predictive evidence of validity
C) evidence of construct validity
D) convergent evidence of validity

Accepted Answer

Construct validity refers to the extent to which a measure assesses the construct it purports to measure. When an underlying theory explains the relation between a predictor and a criterion based on a psychological theory, it provides evidence that the predictor and criterion are measuring the same underlying construct, thus providing evidence of construct validity.

Question 6

In 1959, Campbell and Fiske designed a method for collecting evidence of reliability, convergent validity, and discriminant validity in one study. They called it the ______.
A) exploratory method of factor analysis
B) confirmatory method of factor analysis
C) discriminatory method
D) multitrait-multimethod design

Accepted Answer

Campbell and Fiske designed the multitrait-multimethod design to collect evidence of reliability, convergent validity, and discriminant validity in one study.

Question 7

When the scores on a test correlate strongly with scores on other tests that measure the same construct, we say the test has ______.
A) evidence of validity based on content
B) evidence of validity based on relations with external criteria
C) convergent evidence of validity
D) discriminant evidence of validity

Accepted Answer

Convergent evidence of validity refers to the degree to which a test correlates with other tests that measure the same construct. Therefore, when scores on a test correlate strongly with scores on other tests that measure the same construct, we say the test has convergent evidence of validity. Option A "evidence of validity based on content" is not applicable here as it refers to the extent to which a test covers the domain of interest. Option B "evidence of validity based on relations with external criteria" is also not the best choice as it refers to the ability of the test to predict future performance on a related criterion. Option D "discriminant evidence of validity" refers to the degree to which a test does not correlate with other tests that measure different constructs.

Question 8

If the correlation between social studies test scores and statistics test scores is zero (or not statistically significant), then the social studies test has demonstrated ______.
A) convergent evidence of validity
B) concurrent evidence of validity
C) discriminant evidence of validity
D) evidence of face validity

Accepted Answer

A zero correlation between social studies test scores and statistics test scores suggests that the tests are measuring different constructs and do not share a common variance. This provides evidence of discriminant validity, indicating that the social studies test is able to distinguish between the construct it is intended to measure and other related constructs. Convergent validity refers to the degree to which measures of the same construct are correlated with each other, so it does not apply here. Concurrent validity refers to the extent to which a measure is related to a criterion measure at the same time, which is also not applicable in this scenario. Face validity refers to the degree to which a test appears to measure what it is intended to measure based on its superficial characteristics, and is not a relevant concept in determining the relationship between tests.

Question 9

If test scores correlate with measures of constructs that an underlying theory says are related, then we say the test has ______.
A) convergent evidence of validity
B) discriminant evidence of validity
C) evidence of validity based on content
D) concurrent evidence of validity

Accepted Answer

Convergent evidence of validity refers to the degree to which test scores correlate with measures of constructs that an underlying theory says should be related. Therefore, the best choice is A.

Question 10

Who defines constructs?
A) the American Psychological Association
B) leading researchers in the field
C) can vary from researcher to researcher
D) must not be allowed to vary

Accepted Answer

While the American Psychological Association may provide guidance on constructs, ultimately constructs can vary from researcher to researcher based on their theoretical perspective and research goals. Leading researchers may also have an influence on defining constructs, but there is still room for variation and individual interpretation. It is important to have some level of consistency, but complete standardization is not necessary or possible.

Question 11

How did the APA traditionally define construct validity?
A) the strength of the relationship between a test and a criterion
B) the strength of the relationship between the test and itself
C) the extent to which the test represents all parts of the test domain
D) the extent to which the test measures a theoretically based on phenomenon

Accepted Answer

The traditional definition of construct validity according to APA is the extent to which a test measures a theoretically based phenomenon. This definition emphasizes the importance of theoretical frameworks in test development and the need for tests to measure what they claim to measure.

Question 12

Which one of the following is an abstract construct?
A) job satisfaction
B) job turnover
C) days absent in a 30-day period
D) number of customer complaints in one week

Accepted Answer

Job satisfaction is an abstract construct because it is a subjective feeling or attitude that cannot be directly observed or measured. Job turnover, days absent in a 30-day period, and number of customer complaints are all concrete constructs that can be directly observed and counted.

Question 13

When test users accept evidence of construct validity, they must also accept what?
A) underlying definition of the construct used in the validation process
B) evidence of validity for other tests of similar constructs
C) test as valid for all uses
D) validity of test takers' scores on the test

Accepted Answer

Test users must accept the underlying definition of the construct used in the validation process in order to accept evidence of construct validity, as this is the foundation for the validation process. While evidence of validity for other tests of similar constructs may be useful, it is not necessary for test users to accept in order to accept evidence of construct validity for a specific test. Test users also cannot assume that a test is valid for all uses, as validity is specific to the construct being measured and the context in which the test is administered. Similarly, test users cannot assume the validity of individual test takers' scores on the test without further evidence of reliability and validity for individual score interpretation.

Question 14

When test scores do not correlate with unrelated constructs, there is ______.
A) convergent evidence of validity
B) discriminant evidence of validity
C) evidence of validity based on relations with external criteria
D) evidence of face validity

Accepted Answer

When test scores do not correlate with unrelated constructs, it indicates that the test has discriminant evidence of validity, i.e., it can distinguish between concepts that are not related.

Question 15

Which one of the following would be most likely to establish that a test is grounded in psychological theory?
A) the correlation between test score and external criteria
B) the correlation between the test scores of the same people at two different points in time
C) a high coefficient alpha from a test of internal consistency
D) evidence of validity based on the test's relationship with other constructs

Accepted Answer

Evidence of validity based on the test's relationship with other constructs is the most likely way to establish that a test is grounded in psychological theory. This involves demonstrating that the test scores are related to other constructs or variables in a way that is consistent with the underlying theory. This approach is commonly used to establish construct validity, which is the extent to which a test measures the psychological construct or attribute it was designed to measure. A high coefficient alpha from a test of internal consistency (C) would suggest that the test items are measuring a single construct consistently, but this alone does not establish that the construct is grounded in psychological theory. The correlation between test scores and external criteria (A) may provide some evidence of predictive validity, but again, this alone may not establish that the construct is grounded in psychological theory. The correlation between the test scores of the same people at two different points in time (B) may provide evidence of test-retest reliability, but this does not directly address whether the test is grounded in psychological theory.

Question 16

What did theorists challenge about using validity evidence based on test content and/or validity evidence based on relationships with criteria to establish test validity?
A) They challenged the use of validity based on content because it was not based on statistical analysis.
B) They challenged validity based on relationships with criteria because it did not require reliable tests.
C) They challenged both because the test was not directly being linked to an accepted theory of psychological behavior.
D) They challenged both because they did not rely on accepted ethical standards for testing.

Accepted Answer

Theorists challenged both methods of establishing test validity because they believed that the validity evidence based on test content did not directly link the test to an accepted theory of psychological behavior, and the validity evidence based on relationships with criteria did not require that the test be reliable. As a result, they argued that both methods were not sufficient for establishing test validity.

Question 17

We can divide the process of establishing evidence of construct validity into two parts which include ______.
A) collecting data and analyzing the data
B) gathering theoretical evidence and gathering psychometric evidence
C) interviewing study participants and testing those participants
D) proposing a hypothesis and proving that

Accepted Answer

The two parts of establishing evidence of construct validity are gathering theoretical evidence (such as examining the construct's relationship with other variables in the literature) and gathering psychometric evidence (such as analyzing the construct's factor structure and reliability through statistical techniques). Collecting data and analyzing it, interviewing participants, and proposing and proving hypotheses may be involved in the process, but they are not the two main parts.

Question 18

Which one of the following evidences for validity the textbook suggests is most associated with the traditional notion of construct validity?
A) evidence based on test content
B) evidence based on internal structure
C) evidence based on relations with other variables
D) evidence based on response processes

Accepted Answer

The answer of Which one of the following evidences for...

Question 19

When a group of test items all share something in common that accounts for the high correlations among them, we can say they all share a common ______.
A) cause
B) theory
C) nomological network
D) factor

Accepted Answer

When a group of test items share something in common that explains their high correlations, we can say that they share a common factor. The other options are not as appropriate in this context - cause implies a direct relationship whereas a factor is an underlying construct, theory is a broader explanation and nomological network refers to the interrelationship among constructs in a larger system.

Question 20

Which two validation strategies below help us to establish evidence of construct validity?
A) analysis of variance and multitrait, multimethod analysis
B) convergent evidence of validity and discriminant evidence of validity
C) coefficient alpha and test-retest reliability
D) construct explication and nomological networks

Accepted Answer

Convergent evidence of validity and discriminant evidence of validity are two validation strategies that help us to establish evidence of construct validity. Convergent evidence of validity is the extent to which a measure correlates with other measures of the same construct. Discriminant evidence of validity is the extent to which a measure does not correlate with measures of other constructs.

Quiz 8: How Do We Gather Evidence of Validity Based on a Tests Relation to Constructs

Defining or explaining a psychological construct is referred to as ______.

Which one of the following coefficients is NOT found in a multitrait-multimethod correlation matrix?

In 1954, the American Psychological Association (APA) published recommendations that suggested a new method for establishing validity in which the researcher provides evidence that the test measures behavior predicted by a psychological theory. What did the APA call this evidence?

When a researcher chooses three constructs that are unrelated in theory and three types of tests such as objective, projective, and a peer rating to measure each of the constructs, she is conducting a ______.

When an underlying theory explains the relation between a predictor and a criterion based on a psychological theory, there is ______.

In 1959, Campbell and Fiske designed a method for collecting evidence of reliability, convergent validity, and discriminant validity in one study. They called it the ______.

When the scores on a test correlate strongly with scores on other tests that measure the same construct, we say the test has ______.

If the correlation between social studies test scores and statistics test scores is zero (or not statistically significant) , then the social studies test has demonstrated ______.

If test scores correlate with measures of constructs that an underlying theory says are related, then we say the test has ______.

Who defines constructs?

How did the APA traditionally define construct validity?

Which one of the following is an abstract construct?

When test users accept evidence of construct validity, they must also accept what?

When test scores do not correlate with unrelated constructs, there is ______.

Which one of the following would be most likely to establish that a test is grounded in psychological theory?

What did theorists challenge about using validity evidence based on test content and/or validity evidence based on relationships with criteria to establish test validity?

We can divide the process of establishing evidence of construct validity into two parts which include ______.

Which one of the following evidences for validity the textbook suggests is most associated with the traditional notion of construct validity?

When a group of test items all share something in common that accounts for the high correlations among them, we can say they all share a common ______.

Which two validation strategies below help us to establish evidence of construct validity?