JPSM MPSDS Seminar Series
Accounting for Non-ignorable Sampling and
Nonresponse in Statistical Matching
Danny
Pfeffermann retired as the National Statistician
and Director General of Israel's CBS. He is Professor Emeritus of Statistics at
the Hebrew University of Jerusalem and Professor of Social Statistics at the
University of Southampton.
His
main research areas are: Analytic inference from complex sample surveys;
Seasonal adjustment and trend estimation; Small area estimation; Inference
under informative sampling and nonresponse and more recently; Mode effects and
Proxy surveys.
Professor
Pfeffermann published about 80 articles in leading statistical journals and
co-edited the two-volume handbook on Sample Surveys. He is Fellow of the
American Statistical Association (ASA), the International Statistical Institute
(ISI) and the Institute of Mathematical Statistics (IMS), and recipient of
several international awards.
Abstract
Data
for statistical analysis is often available from different samples, with each
sample containing measurements on only some of the variables of interest.
Statistical matching attempts to generate a fused database containing matched
measurements on all the target variables. In this article, we consider the use
of statistical matching when the samples are drawn by informative sampling
designs and are subject to not missing at random nonresponse. The problem with
ignoring the sampling process and nonresponse is that the distribution of the
data observed for the responding units can be very different from the
distribution holding for the population data, which may distort the inference
process and result in a matched database that misrepresents the joint
distribution in the population. Our proposed methodology employs the empirical
likelihood approach and is shown to perform well in a simulation experiment and
when applied to real sample data.
**Joint paper with Daniela Marella, to appear
in International Statistical Review