Deck 7: Reliability and Validity

Question 1

A researcher determined that two variables were correlated. Which of the following statements would be a true statement about the strength of this relationship:

A) A correlation of .3 is stronger than a correlation of .75
B) A correlation of -1.0 equals a correlation of 0.0
C) A correlation of -.75 is stronger than a correlation of .3
D) A correlation of 1.0 is stronger than a correlation of -1.0.

Answer 1

A correlation of -.75 is stronger than a correlation of .3

Question 2

The Pearson r correlation coefficient is used to measure

A) The test re-test reliability of a test
B) The predictive validity of a test
C) The construct validity of a test
D) All of the above

Answer 2

All of the above

Question 3

This exam is an example of a ______________ test; whereas the NEO-PI-R is an example of a____________ test.

A) Reliable; valid
B) Valid; reliable
C) Norm referenced, criterion- referenced
D) Criterion- referenced; norm-referenced

Answer 3

Criterion- referenced; norm-referenced

Question 4

According to classical test theory which of the following statements is true?

A) A test score is equal to the true score plus or minus test error
B) Reliability is an estimate of the ratio of true test score variance to observed test variance
C) The more reliable a test is the less unsystematic error is associated with it.
D) All of the above

Question 5

A common internal consistency reliability measure is:

A) The T-test
B) Standard error of measurement
C) Coefficient alpha
D) Pearson R squared

Question 6

The developer of a new personality test wanted the test's norms to be comprised of certain percentages of different racial-ethnic groups, therefore she used a ___________ technique for obtaining the standardization group.

A) Stratified sampling
B) U.S. Census info generating
C) Random sampling.
D) Criterion cluster driven.

Question 7

A counselor researcher developed a new PTSD test. She gave the test to 100 clients and also gave those same clients two other tests, the Beck Anxiety Inventory and the Mini Mental Status Evaluation. She correlated the scores of the tests in order to assess the ____________ of her PTSD test.

A) Internal Consistency
B) Construct validity
C) Face Validity
D) Split-half reliability

Question 8

The concept of reliability refers to:

A) The internal stability of a test or measure
B) The degree to which a test measures what it purports to measure
C) How consistent the test taker is in answering test questions
D) None of the above.

Question 9

The reliability of a test can be affected by:

A) The number of individuals in the normative sample
B) The number of items on the test
C) The degree of difficulty of the test items
D) The response format of the test

Question 10

If a test has construct validity then which of the following statements are true?

A) The test correlates highly with other tests that measure the same and different constructs
B) The test correlates highly with another test measuring a different construct and has little correlation with another test measuring a similar construct
C) The test correlates highly with another test measuring the same construct and has little correlation with a test measuring a different construct
D) The validity coefficient is greater than the test's reliability coefficient

Question 11

When using psychological tests to make predictions about an individual's future status, for example diagnosis, or behavior, tests will be most helpful when the condition of behavior in question has a base rate of:

A) 99%
B) 50% approximately
C) Less than 10%
D) Between 1 and 10%

Question 12

Counselors may decide to use a test based on its sensitivity. Sensitivity refers to:

A) The cultural sensitivity of a test
B) The ability of a test to have few false negatives
C) The ability of a test to accurately identify an individual as having a condition or disorder
D) The ability of a test to accurately identify as not having a condition or disorder

Question 13

The concept of incremental validity refers to:

A) The ability of multiple assessments used in combination to make accurate predictions
B) How many pieces of information a counselor can accurately recall from an assessment
C) A statistical process for measuring the accuracy of a test based on its size
D) An assessment battery in which each test that is used has greater predictive validity than the previous one

Question 14

The statistic that quantifies the degree to which a test can predict the range of scores on some kind of outcome measure or criterion is the:

A) Coefficient of Determination
B) Regression factor
C) Alpha Coefficient
D) Kuder Richardson Scale

Question 15

What are the three different types of reliability and how do they differ?

Question 16

How do test developers demonstrate evidence of their test's construct validity?

Question 17

What does the concept of incremental validity mean?

Question 18

What does the correlation coefficient measure?

Question 19

Which psychometric factors need to be considered when choosing a test or measure?