Effects of Truncating a Reference Population on Correction of Validity Coefficients for Range Restriction

Abstract

The goal of the Joint-Service Job Performance Measurement Project is to link enlistment standards and job performance. Central to the analysis for this project is the computation and interpretation of correlation coefficients. The correlation between the Armed Services Vocational Aptitude Battery (ASVAB) subtests and performance measures is used to evaluate predictive validity of the ASVAB, and hence the justification for basing qualifying standards on the ASVAB. Correlation coefficients based on samples from occupational specialties that differ in qualification standards cannot be compared. The sample coefficients need to be put on the same metric by correcting them to a common reference population. The purpose of this analysis is to evaluate the effects of truncating the reference population on the correlation coefficients and on the intercorrelation of performance measures. Population-wide estimates were computed in the full population and in the truncated population with the bottom 10 percent deleted.

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1985
Accession Number
ADB103741

Entities

People

  • Milton H. Maier

Organizations

  • Center for Naval Analyses

Tags

Communities of Interest

  • Human Systems

DTIC Thesaurus Topics

  • Abstracts
  • Classification
  • Data Science
  • Information Science
  • Marine Corps
  • Military Research
  • Minority Groups
  • Performance Tests
  • Personnel Management
  • Personnel Selection
  • Psychological Tests
  • Qualifications
  • Second World War
  • Security
  • Standards
  • Statistics
  • Truncation

Readers

  • Psychometric Testing or Psychological Assessment.
  • Regression Analysis.