In order to understand predictive validity it may first be useful to understand the concept of correlation. Correlation is a statistical measure of the degree to which two variables (such as test scores) are related.
It is measured using the pearson correlation coefficient (r), with a possible range of r values between -1 and +1. An r value of +1 represents a perfect perfect positive correlation, in which an increase in one variable is perfectly related to an increase in another, or a decrease in one variable is perfectly related to a decrease in another.
In personnel selection, predictive validity is the extent to which the assessment measure correlates with a future measure of job performance. It therefore represents the ability of an assessment technique to predict future job performance. It follows that the goal in selection is to find an assessment measure that obtains an r value that is as close to +1 as possible when correlated with the job performance measure.
In a predictive validity study, assessment scores are correlated with job performance scores collected a year or so later. Assessment scores can be taken from techniques such as work samples, tests of General Mental Ability, structured interviews, etc. Job performance is often measured using criterion such as supervisory ratings of job performance, job-related learning, sales records, and performance in job training programs.
Ideally, high assessment scores will obtain strong correlations with job performance scores taken at a later date, and the selection method will be considered a valid prectictor of job performance.
In practice, correlations obtained from predictive validity studies vary greatly and are typically quite low. In their summary of predictive validity studies for 19 personnel assessment measures, Schmidt & Hunter (1) report (r) values ranging from .02 for graphology to .54 for work sample tests.
They also discuss the benefits of measuring predictive validity, stating that, in terms of practical value, predictive validity is the most important property of a personnel assessment method. This claim is based on research which has shown that the predictive validity coefficient is directly proportional to the practical economic value of the assessment method (2, 3), and that use of hiring methods with increased predictive validity leads to substantial increases in employee performance (4).
1. Schmidt, F.L. & Hunter, J.E. (1998) The Validity and Utility of Selection Methods in Personnel Psychology- Practical and Theoretical Implications of 85 Years of Research Findings. (Psychological Bulletin, 124(2), 262-274)
2. Brogden, H. E. (1949). When testing pays off.( Personnel Psychology, 2, 171—183.)
3. Schmidt, F. L., Hunter, J. E., McKenzie, R. C. & Muldrow, T. W. (1979). The impact of valid selection procedures on work-force productivity.(Journal of Applied Psychology, 64, 609—626.)
4. Hunter, J. E., Schmidt, F. L. & Judiesch, M. K. (1990). Individual differences in output variability as a function of job complexity.(Journal of Applied Psychology, 75, 28—42.)
|
