The use of supervisory assessments of performance during the course of a test validation study raised statistical problems in the handling of variable degrees of racial bias on the part of the raters and differing lengths of job tenure on the part of the employees. This paper describes a method of solving these problems which permitted use of 100% of the available supervisory ratings.
References
1.
BaehrM. E.The appraisal of job performance. Chicago: Industrial Relations Center, Univer. of Chicago, 1968. (Occasional Paper No. 27-R1).
2.
BaehrM. E.National validation of a selection test battery for male transit bus operators. Final report, Industrial Relations Center, Univer. of Chicago, 1976.
3.
FinnJ. O.Multivariance: univariate and multivariate analysis of variance, covariance, and regression. Chicago: National Educational Resources, 1974.
4.
FisherR. A.Statistical methods for research workers. (13th ed., rev.) New York: Hafner, 1958. (No. V. Biological monographs and manuals, CreweF. A. E., General Editor).
5.
SaundersD. R.On the statistical treatment of remarkable data. Educational and Psychological Measurement, 1970, 30, 533–545.
