
Evaluation and Selection of Models for Attrition Nonresponse Adjustment Eric V. Slud, Leroy Bailey Abstract: This article considers a longitudinal survey like the U.S. Survey of Income and Program Participation (SIPP), with successive “waves” of data collection from sampled individuals, in which nonresponse attrition occurs and is treated by weighting adjustment, either through adjustment cells or a model like logistic regression in terms of auxiliary covariates. We measure the biases in estimated initialwave (Wave 1) attribute totals between the surveyweighted estimator in the first wave and the weightadjusted estimator for the same Wave 1 item total based on laterwave respondents. Three new metrics of quality are defined for models used to adjust a longitudinal survey for attrition. The metrics combine estimated betweenwave adjustment biases based on subsets of the sample, relative to the estimated total, for various survey items. The maximum of the biases for estimated totals of a survey item is calculated from the weightadjusted subtotal of the first j sample units, as j ranges from 1 to the size of the entire (Wave 1) sample, after a random reordering either of the whole sample or of the units within distinguished cells (which are then also randomly reordered); and the average over reorderings of the maximal adjustment bias is divided by the estimated Wave 1 attribute total to give the metric value. Confidence bands for the metrics are estimated, and the metrics are applied to judge the quality of and to select among a collection of logisticregression models for attrition nonresponse adjustment in SIPP 96. Keywords: adjustment cell, logistic regression, weighting, random reordering, raking, subdomain
