Identifying Keys and Scoring Algorithms to Enhance Personality Scale Validity

Abstract

The U.S. Army Cadet Command uses personality scales that have been validated against the Cadet Order of Merit Score, to help award U.S. Army Reserve Officer Training Corps scholarships. To improve the utility of these measures, the U.S. Army Research Institute for the Behavioral and Social Sciences (ARI) is evaluating alternate procedures that can be used to key and compute scale scores for these measures. Analyses were conducted using a cross-validation design to identify near-optimal scoring keys to validate shape and dot product scores for twenty-one personality scales against the Cadet Order of Merit Score. Subsequent regression analyses compared the efficacy of using dot product scores, profile similarity metrics, and distance scores for individual scales and the battery. Scale results show substantial validity gains for most scales when using the more sophisticated scoring approaches. Battery validity estimates were high for profile similarity metrics scores and dot product scores adjusted for respondent scatter and elevation effects, while modest results were obtained for conventional distance scores (Rpsm = .61 and Rdot = .61 vs Rdist = .45).

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 2021
Accession Number
AD1156386

Entities

People

  • Benjamin S. Kerner
  • Oren R. Shewach
  • Peter J. Legree
  • Zach Traylor

Organizations

  • Human Resources Research Organization

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • African Americans
  • Algorithms
  • Anthropology
  • Behavioral Sciences
  • Coefficients
  • Descriptive Analytics
  • Ethnic Groups
  • Information Science
  • Military Research
  • Psychology
  • Real Numbers
  • Regression Analysis
  • Reserve Officer Training Corps
  • Scholarships
  • Social Sciences
  • Statistics
  • Training

Fields of Study

  • Psychology

Readers

  • Psychometric Testing or Psychological Assessment.