Analytic Methods for Adjusting Subjective Rating Schemes

Abstract

Subjective evaluations of individual performances by supervisors are subject to bias. This report develops statistical and econometric techniques for correcting biases in models of individual performance using a variant of the Classical linear regression model. A multi-scale model is proposed to deal with two types of bias: location bias when an individual's performance is systematically overestimated or underestimated, and scale bias when differences among individuals rated are exaggerated or minimized. Several specific multi- scale estimating techniques are developed, and multi-scale estimators are applied to the problem of estimating the cost of on-the-job training in the military.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1976
Accession Number
ADA026887

Entities

People

  • Gary R. Nelson
  • Richard V. L. Cooper

Organizations

  • RAND Corporation

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Asymptotic Normality
  • Computations
  • Consistency
  • Corporations
  • Covariance
  • Data Science
  • Department Of Defense
  • Information Science
  • Job Training
  • Probability
  • Random Variables
  • Regression Analysis
  • Statistical Algorithms
  • Statistical Analysis
  • Statistics
  • Test And Evaluation
  • Training

Fields of Study

  • Mathematics

Readers

  • Approximation Theory.
  • Instructional Design and Training Evaluation.
  • Life Cycle Cost Analysis