Weighting is a common form of unit nonresponse adjustment in sample surveys where entire questionnaires are missing due to noncontact or refusal to participate. Weights are inversely proportional to the probability of selection and response. A common approach computes the response weight adjustment cells based on covariate information. When the number of cells thus created is too large, a coarsening method such as response propensity stratification can be applied to reduce the number of adjustment cells. Simulations in Vartivarian and Little (2002) indicate improved efficiency and robustness of weighting adjustments based on the joint classification of the sample by two key potential stratifiers: the response propensity and the predictive mean, both defined in Section 2. Predictive mean stratification has the disadvantage that it leads to a different set of weights for each key outcome. However, potential gains in efficiency and robustness make it desirable to use a joint classification. Here, we consider the efficiency and robustness of weights that jointly classify on the response propensity and predictive mean, but the base the predictive mean dimension on a single canonical outcome variable.


Design of Experiments and Sample Surveys | Statistical Methodology | Statistical Theory