Week 4

Question 1

The practical importance of a test depends on what?

Answer 1

The quality of the decision made on the basis of the test

To determine what the test adds to the decision, compare the decisions made with and without the test.

Question 2

What is the base rate in the context of test utility?

Answer 2

Proportion of persons that is suited for the job within the applicant pool

Base rate equals the success ratio when selecting by chance.

Question 3

What is the success ratio?

Answer 3

Proportion of the hired applicants that is successful

Example: Success ratio = 35% of the hired people is successful.

Question 4

What does a selection ratio indicate?

Answer 4

Proportion of applicants that is being accepted for the job

Example: Selection ratio = 23% of the applicants is accepted.

Question 5

True or false: A test with low predictive validity has no incremental value.

Answer 5

FALSE

Even tests with relatively low validity can have incremental validity under certain conditions.

Question 6

What is the utility of a test based on?

Answer 6

Aim to hire successful candidates and reject unsuccessful candidates

The test is not perfect, thus also leads to incorrect decisions.

Question 7

What are the four outcomes of a decision based on a test?

Answer 7

• False negative
• Hit
• Hit
• False positive

A: incorrectly rejected, B: correctly hired, C: correctly rejected, D: incorrectly hired.

Question 8

What is the incremental value of a test?

Answer 8

The contribution of a test to decisions made

This is partly dependent on context factors.

Question 9

What should be considered when deciding to use a test in a selection procedure?

Answer 9

• Costs/benefits
• Selection procedures require investments
• Expected change in success ratio versus costs

Unsuccessful employees/students are expensive.

Question 10

What does predictive validity check?

Answer 10

The quality of your data

It involves checking criterion measures and existing information.

Question 11

What happens when the base rate is very high or very low?

Answer 11

The test is not useful

Almost everyone can do the job or almost no one can do the job.

Question 12

What is the aim of utility models?

Answer 12

To optimize the success ratio

This includes the proportion of persons that is successful.

Question 13

What is the Taylor-Russell table used for?

Answer 13

Estimation of the incremental value of a test

It provides the success ratio for a particular base rate, selection ratio, and predictive validity.

Question 14

Fill in the blank: The success ratio is the proportion of the hired applicants that is __________.

Answer 14

successful

Example: Success ratio = 35% of the hired people is successful.

Question 15

What is the utility of a test based on a table?

Answer 15

Aim to hire successful candidates and reject unsuccessful candidates

The test is not perfect, thus also leads to incorrect decisions.