83%(6)5 out of 6 people found this document helpful
This preview shows page 36 - 40 out of 65 pages.
This chapter begins by describing some important statistical concepts which relate to selection testing. These concepts are important. While you do not need to know the theory, nor how these statistical measures are calculated, you should have a good understanding of the concepts. The purpose of this chapter is stated very clearly in the Introduction - "The purpose of this chapter is to familiarize you with ways to minimize errors in employee selection and placement, and in doing so improve your company's competitive position." An incorrect selection and/or placement decision can be very costly for an organization, in fact, some estimates of a incorrect hiring decision run into the thousands, or even millions of dollars.
Selection Method Standards (Know and understand these!) Five generic standards which should be met in any selection process: Reliability - the consistency of a performance measure; the degree to which a performance measure is free from random error; the degree of dependability, consistency, or stability of scores on a measure used in selection ; reliability deals with errors of measurement (Gatewood, Field, and Barrick, 2011, p. 104); measured by correlation coefficient; regardless of what we are measuring, the goal is to have highly reliable measures Correlation coefficient - a measure of the degree to which two sets of numbers are related Perfect Positive Relationship = +1 Perfect Negative Relationship = No relationship = 0 Random error - think of random error as unreliability or disturbance Test- retest reliability - the correlation between scores on two administration of a test to the same subject; higher correlation indicates high reliability Validity - the extent to which a performance measure assesses all of the relevant, and only the relevant, aspects of job performance; a measure must be reliable to have validity; reliability is a necessary but insufficient condition for validity Criterion-
1. b. c. 2.a. i. a.i. ii. iii. -1 ii. 1) Superior to concurrent validity due to: