Question 1

Test J has a correlation of .60 with test K and a correlation of .30 with test L. test J accounts for how much less or more variability in test K as it does in test L?

Accepted Answer

Test J accounts for four times as much variability in test K than it does in test L. Each correlation is converted to a percentage and then the first percentage is divided by the second. A correlation of .60 converts to 36%. A correlation of .30 converts to 9%. Divide 36 by 9 for a result of 4.

Question 2

There are three ways to measure reliability in test construction. Which of the following is NOT one of those ways?

Accepted Answer

Statistical analysis is the method of analyzing results from a study, but does not determine reliability. The following are measures of reliability: alternate forms of the same test produce similar correlations; scores and correlation are similar for each test when it is given twice at separate times; correlations between several items in a test designed to measure the same variable.

Question 3

Test construction requires that tests have both validity and reliability. What is the Spearman-Brown prophecy formula used for in this context?

Accepted Answer

The Spearman-Brown prophecy formula is used to predict increase in reliability of a test if it were longer than it is. Specifically, the formula is used in the context of split-half reliability to account for the reduction in reliability resulting from this method of testing score consistency.

Question 4

In statistical test construction, factorial design allows for analysis of the effect of each factor on the response variable, as well as the effect of interactions between factors on the response variable. If a factorial design yields main and interaction effects, how should results be interpreted?

Accepted Answer

When analyzing results from a factorial design test, analyze the main effect while keeping in mind the interaction effect. ANOVA or regression analysis is the appropriate choice for this test.

Question 5

Test construction requires that tests have both validity and reliability. Split-half reliability is useful in determining the reliability of the following tests except for the:

Accepted Answer

Split-half reliability is not useful in determining the reliability of speeded tests, which have time limits, because these tests are typically composed of questions that are easy to answer correctly. Splitting the test results in two would give an artificially high estimate of reliability.

Question 6

Test construction requires that tests have both validity and reliability. If reliability of a test is perfect (1.00), what is the standard error of measurement?

Accepted Answer

Standard error of measurement would be 0.0 if a test had perfect reliability. Calculating standard error of measurement is one way of estimating reliability, so a theoretical test with perfect reliability has no standard of error. In reality, no test would have perfect reliability.

Question 7

A questionnaire designed to assess level of anxiety is administered. When analyzing results, researchers obtain a reliability coefficient of .65. What should they do with this information?

Accepted Answer

Using a more diverse group of subjects will increase test reliability, since it will increase the range of scores. Some action should be taken to address this; the lowest acceptable reliability coefficient is .70 and many researchers require a higher reliability coefficient.

Question 8

Test construction involves determining the reliability of a test-how consistent and dependable obtained scores are. What does the classical test theory state about reliability?

Accepted Answer

Classical test theory states that total variability equals true score variability plus error variability. Total variability is always 100% and reliability is the proportion of true score variability (if true score variance is 70%, reliability is .70).

Question 9

One of the most important tasks of human resources is to obtain and analyze information about a particular job (tools and training needed, what the requirements of the job are). There are a number of ways to obtain this data. Which of the following techniques involves determining specific actions that lead to desirable or undesirable consequences on the job?

Accepted Answer

The critical incident technique involves determining specific actions that lead to desirable or undesirable results on the job. For example, actions with desirable consequences for a customer service representative might include friendly and professional greetings and providing useful information to customers.

Question 10

Employee selection is based on a range of information and assessment that employers gather and conduct, one of which is interviews. Interviews have the worst criterion-related validity, especially when unstructured. There are a number of biases that can occur in an unstructured interview. Which of those biases is defined as an interview's ratings of a candidate being affected by their rating of the previous candidate?

Accepted Answer

The contrast effect occurs when an interviewer rates a candidate differently (either positively or negatively) because of the rating of the previous candidate. For example, a qualified candidate is rated as mediocre because the previously interviewed candidate was extremely well-qualified.

Question 11

Employee selection is based on a range of information and assessment that employers gather and conduct, one of which is interviews. Interviews have the worst criterion-related validity, especially when unstructured. There are a number of biases that can occur in an unstructured interview. Which of those biases refers to the occurrence of an interviewer determining that an individual is generally competent and well-qualified because they are notably more attractive than other candidates?

Accepted Answer

The halo effect involves generalizing overall qualities of a candidate based on one specific characteristic; this often occurs when a candidate is particularly attractive or unattractive.

Question 12

Different assessment tests are used in evaluating candidates, including cognitive ability tests, aptitude tests, and personality tests. Which of the following tests is a cognitive ability test?

Accepted Answer

The Wonderlic test is a standardized cognitive ability test used to assess problem-solving and learning aptitude. Situational judgment testing refers more to the way tests are designed than to their content (content may be similar to a cognitive ability test, but the manner of delivery is specifically tailored, not standardized). Typing tests are aptitude tests. Work sample tests are a chance for a candidate to demonstrate sample work behavior.

Question 13

Different assessment tests are used in evaluating candidates, including cognitive ability tests, aptitude tests, and personality tests, among others. What does Holland's self-direct search test for?

Accepted Answer

Holland's self-directed search test inventories career interests; it is based on the idea that there are most people can be categorized in one of six occupational types (Realistic, Investigative, Artistic, Social, Enterprising, and Conventional). This test is not a good predictor of job success, but is positively correlated with job satisfaction.

Question 14

Neuropsychological testing is used to determine neurological function, screen for various disorders, or assess brain damage. Which of the following neuropsych tests is used to screen for brain damage and developmental disorders and has high validity?

Accepted Answer

The Bender Visual Motor Gestalt Test is used to screen for brain damage developmental disorders, evaluate visual-motor maturity, and is thought to have high levels of reliability and validity.

Question 15

Neuropsychological testing is used to determine neurological function, screen for various disorders, or assess brain damage. Which of the following tests is used to assess physical aspects and location of neurological damage?

Accepted Answer

The Halstead-Reitan Neuropsychological Battery is a collection of tests used to assess physical aspects and location of neurological damage. It includes Trails A and B, Rhythm Test, Speech Sounds Perception Test, and Halstead Category Test, among others.

Question 16

Neuropsychological testing is used to determine neurological function, screen for various disorders, or assess brain damage. The Halstead-Reitan Neuropsychological Battery is used to assess physical aspects and location of neurological damage. Which of the following is NOT included in this combination of tests?

Accepted Answer

The Figural Fluency Test is not part of the Halstead-Reitan Neuropsychological Battery. Known as the Ruff Figural Fluency Test, this is a nonverbal fluency test that assesses frontal lobe function and is thought to be sensitive to the right frontal lobe.

Question 17

You want to administer an intelligence test to a 15-year-old who has significant performance problems in school to determine if there is a potential cognitive cause. What is the most appropriate test option?

Accepted Answer

Stanford-Binet is the best option for testing a teenager who has significant performance problems in school. The WAIS-III is designed for individuals from age 16 to 89. The WISC-IV test is a children's intelligence test. However, since this evaluation is related to performance problems, a test with a lower floor and higher ceiling (the Stanford-Binet) is more suitable, as it can better assess both very low and very high IQ scores.

Question 18

The Rorschach personality test aims to assess personality structure. There are a number of scoring systems used. However, each response is usually scored on a variety of dimensions. Which of the following is NOT one of those dimensions?

Accepted Answer

Response time is not one of the dimensions usually scored in a Rorschach test. The four are: content, what category a response belongs to; location, what area of the inkblot was used to develop a response; form quality, how accurate the response is in relation to the form of the inkblot; and developmental quality, the degree of integration for each response.

Question 19

Personality tests are used in both clinical and non-clinical settings. Which of the following tests is the best choice for a business owner to employ in the hiring process?

Accepted Answer

The CPI, or California Psychological Inventory, is most useful for an employer in the hiring process. This test provides a personality profile like the MMPI-2, but uses different scales. Other applications of the CPI include use in vocational and academic counseling, use for predicting success in various occupations, and in use in clinics to evaluate a range of social problems.

Question 20

The MMPI-2 is an objective personality test that uses self-reporting and includes several clinical and validity scales. Someone whose scores suggest distress or an attempt at a cry for help likely scored how on which scale?

Accepted Answer

Someone whose scores suggest distress or an attempt at a cry for help likely scored high on the F scale, which is the infrequency, or "fake bad," scale.

Quiz 1: Assessment and Diagnosis