Predicting high quality AFQT with youth attitude tracking study data.
Rickman, Jackie Lynn
MetadataShow full item record
This thesis demonstrates that Youth Attitude Tracking Study (YATS) data can be used to create a synthetic AFQT classification procedure for distinguishing high quality respondents. Unlike previous methods , the procedure does not rely on interest in the military to predict AFQT category. The estimates are based on an analysis of the YATS data matched with the Defense Manpower Data Center cohort data file using a binomial logistic regression model. The market segment analyzed is 17 to 21 year old males who are either high school graduates or prospective high school graduates . The dependent variable is whether or not a respondent would score above the fiftieth percentile on the Armed Forces Qualification Test. The explanatory variables reflect individual demographic, educational and labor market characteristics at the time of YATS interview. The YATS time frame is restricted to 1983 through 1985 in order to facilitate future bridging of YATS models with models estimated with similar time period data from the National Longitudinal Survey of Youth (NLSY) . Additionally, the models may be used to provide estimates of AFQT quality for more recent YATS respondents.