Events and Seminars : Upcoming Seminars

INFERENTIAL ISSUES IN THE PRESENCE OF IMPUTATION FOR MISSING SURVEY DATA

J.N.K. RAO, PH.D.
Professor Emeritus and Distinguished Research Professor School of Mathematics and Statistics
MONDAY, JANUARY 25, 2016
1:30 p.m.–2:30 p.m., CRB 692

Item nonresponse occurs frequently in sample surveys collecting data on many items. It is customarily handled by some form of imputation to fill in the missing values. However, Imputed values are often treated as if they were true values in making inferences form imputed data sets. Resulting point estimates are often valid but the “naïve” variance estimates can lead to serious underestimation of the true variance even for large samples because the additional variability due to estimating the missing values is not taken into account. Some impressive advances have been made in recent years on making efficient and asymptotically valid inferences from singly imputed data sets. Main purpose of this talk is to present an overview and appraisal of methods for variance estimation under single imputation. Fractional imputation and multiple imputation both use multiple imputed values for a missing item and reduce imputation variance relative to single imputation using only one randomly imputed value. Variance estimation under fractional and multiple imputation will also be studied. Finally, the construction of bootstrap confidence intervals under imputation will be considered.