EFFECTS OF MONOTONE AND NONMONOTONE ATTRITION ON PARAMETER ESTIMATES IN REGRESSION-MODELS WITH EDUCATIONAL DATA - DEMOGRAPHIC EFFECTS ON ACHIEVEMENT, ASPIRATIONS, AND ATTITUDES

Using the High School and Beyond longitudinal study, we investigate th e participation patterns across Sour waves of data. Because nonrespond ents from one wave are recontacted at subsequent waves, both monotone and nonmonotone attrition patterns arise. We discuss correlates of the se two types of attrition in an attempt to describe individuals who ma y be at-risk of attrition. Gender and incomplete participation in the base-year (respondents who exhibit item nonresponse on key variables) are important predictors of later attrition. Estimated effects of mono tone and nonmonotone attrition on parameter estimates in regression mo dels suggest that certain demographic effects will be biased due to sa mple attrition. The evidence for bias is neither pervasive nor consist ent, but suggests a systematic inflation of the Black-White achievemen t disparity.