Multiple Imputation for Combined-Survey Estimation With Incomplete Regressors In One But Not Both Surveys

by Michael S. Rendall, Bonnie Ghosh-Dastidar, Margaret M. Weden, Zafar Nazarov

Download eBook for Free

FormatFile SizeNotes
PDF file 0.7 MB

Use Adobe Acrobat Reader version 10 or higher for the best experience.

Within-survey multiple imputation (MI) methods are adapted to pooled-survey regression estimation where one survey has a larger set of regressors but fewer observations than the other. This adaption is achieved through: (1) larger numbers of imputations to compensate for the higher fraction of missing values; (2) model-fit statistics to check the assumption that the two surveys sample from a common universe; and (3) specificying the analysis model completely from variables present in the survey with the larger set of regressors, thereby excluding variables never jointly observed. In contrast to the typical within-survey MI context, cross-survey missingness is monotonic and easily satisfies the Missing At Random (MAR) assumption needed for unbiased MI. Large efficiency gains in estimates of coefficients for variables in common between the surveys are demonstrated in an application to sociodemographic differences in the risk of experiencing a disabling occupational injury estimated from two nationally-representative panel surveys.

This paper series was made possible by the NIA funded RAND Center for the Study of Aging and the NICHD funded RAND Population Research Center.

This report is part of the RAND Corporation working paper series. RAND working papers are intended to share researchers' latest findings and to solicit informal peer review. They have been approved for circulation by RAND but may not have been formally edited or peer reviewed.

The RAND Corporation is a nonprofit institution that helps improve policy and decisionmaking through research and analysis. RAND's publications do not necessarily reflect the opinions of its research clients and sponsors.