Underadjustment Bias in the Evaluation of Manpower Training
- 1 May 1979
- journal article
- research article
- Published by SAGE Publications in Evaluation Quarterly
- Vol. 3 (2) , 190-218
- https://doi.org/10.1177/0193841x7900300202
Abstract
A review of the literature suggests that choice of control group may have affected the policy implications of the major evaluations of governmental training programs. It is argued that the usual evaluation designs underadjust for preprogram differences between trainees and the control group and thus yield biased estimates of program impact. At tempts to statistically correct for such bias are presented and assessed.Keywords
This publication has 4 references indexed in Scilit:
- Toward a Causal Model Approach for Adjusting for Preexisting Differences in the Nonequivalent Control Group SituationEvaluation Quarterly, 1977
- An Errors-In-Variables Analysis of Managerial Role PerformanceJournal of the American Statistical Association, 1974
- A Nationwide Evaluation of M.D.T.A. Institutional Job TrainingThe Journal of Human Resources, 1968
- Investigations of the SimplexPsychometrika, 1960