Basic Attributes Test (BAT): Operational Pre-Implementation Analysis and Score Equating
Abstract
The Air Force will implement a new pilot candidate selection system. Scores from a multiple aptitude test (Air Force Officer Qualifying Test or AFOQT), a computer-based test (Basic Attributes Test or BAT), and biographical information will be used to compute a pilot candidate selection composite score derived from an equation designed to indicate probability of success in undergraduate pilot training (UPT). The purpose of this study was to equate the experimental and operational tests. The pre-implementation equating was necessary (a) to determine whether the tests measured the same psychological constructs, (b) to compare operational score distributions, and (c) to develop equating tables. Equating was required so that scores from operational tests could be used in proposed pilot candidate selection equations developed on the experimental tests of the BAT. Experimental and operational tests were administered to about 2,000 basic recruits. Analyses were performed at the test score and composite score level and several types of equatings were completed. Adjusted correlations between the experimental and operational BAT tests were acceptable and demonstrated measurement equivalence. Differences in the shapes of the distributions (i.e., skewness, kurtosis) were observed for several of the scores between the two forms. Severals types of equatings (linear, equipercentile, smoothed equipercentile) were performed to develop conversion tables for use during implementation of operational tests. Scores will be renormed to the operational test metric and a new pilot candidate selection composite will be developed after a sufficient number of applicants have been tested and have completed UPT
Document Details
- Document Type
- Technical Report
- Publication Date
- May 01, 1993
- Accession Number
- ADA265885
Entities
People
- Malcolm J. Ree
- Thomas R. Carretta
Organizations
- Armstrong Laboratory