Development of Statistically Parallel Tests by Analysis of Unique Item Variance.

Abstract

A method for developing statistically parallel tests based on the analysis of unique item variance was developed. Unique item variance is determined by the multiple correlation of any item with a set of items in an iterative approach. The approach was successfully implemented on a perceptual ability test and replicated on an attitude scale. (Author)

Document Details

Document Type
Technical Report
Publication Date
May 01, 1976
Accession Number
ADA025848

Entities

People

  • Malcolm James Ree

Organizations

  • Brooks Air Force Base

Tags

Fields of Study

  • Education

Readers

  • Computer Vision.
  • Regression Analysis.