Open Conference Systems, ITACOSM 2019 - Survey and Data Science

Font Size: 
Imputation for the treatment of item nonresponse in surveys: an overview
David Haziza

Building: Learning Center Morgagni
Room: Aula Magna 327
Date: 2019-06-05 01:30 PM – 02:30 PM
Last modified: 2019-05-24

Abstract


The most common way for treating item non-response in surveys is to construct one or more replacement values to fill in for a missing value. This process is known as imputation. We distinguish single from multiple imputation. Single imputation consists of replacing a missing value by a single replacement value, whereas multiple imputation uses two or more replacement values. In the presentation, we will review imputation procedures commonly used in National Statistical Offices as well as the properties of point and variance estimators in the presence of imputed survey data. We will also discuss newer developments in the field including multiply robust procedures.

Full Text: SLIDES