Header

UZH-Logo

Maintenance Infos

A Markov chain Monte Carlo algorithm for multiple imputation in large surveys


Schunk, D (2008). A Markov chain Monte Carlo algorithm for multiple imputation in large surveys. Advances in Statistical Analysis (AStA), 92(1):101-114.

Abstract

Important empirical information on household behavior and household finances, used heavily by researchers, central banks, and for policy consulting, is obtained from surveys. However, various interdependent factors that can only be controlled to a limited extent lead to unit and item nonresponse, and missing data on certain items is a frequent source of difficulties in statistical practice. All the more, it is important to explore techniques for the imputation of large survey data. This paper presents the theoretical underpinnings of a Markov Chain Monte Carlo multiple imputation procedure and outlines important technical aspects of the application of MCMC-type algorithms to large socio-economic datasets. In an exemplary application it is found that MCMC algorithms
have good convergence properties even on large datasets with complex patterns of missingness, and that the use of a rich set of covariates in the imputation models has a
substantial effect on the distributions of key financial variables.

Abstract

Important empirical information on household behavior and household finances, used heavily by researchers, central banks, and for policy consulting, is obtained from surveys. However, various interdependent factors that can only be controlled to a limited extent lead to unit and item nonresponse, and missing data on certain items is a frequent source of difficulties in statistical practice. All the more, it is important to explore techniques for the imputation of large survey data. This paper presents the theoretical underpinnings of a Markov Chain Monte Carlo multiple imputation procedure and outlines important technical aspects of the application of MCMC-type algorithms to large socio-economic datasets. In an exemplary application it is found that MCMC algorithms
have good convergence properties even on large datasets with complex patterns of missingness, and that the use of a rich set of covariates in the imputation models has a
substantial effect on the distributions of key financial variables.

Statistics

Citations

26 citations in Web of Science®
31 citations in Scopus®
Google Scholar™

Altmetrics

Downloads

166 downloads since deposited on 01 Dec 2008
30 downloads since 12 months
Detailed statistics

Additional indexing

Item Type:Journal Article, refereed, original work
Communities & Collections:03 Faculty of Economics > Department of Economics
Dewey Decimal Classification:330 Economics
Language:English
Date:February 2008
Deposited On:01 Dec 2008 16:04
Last Modified:05 Apr 2016 12:36
Publisher:Springer
ISSN:1863-8171
Additional Information:The original publication is available at www.springerlink.com
Publisher DOI:https://doi.org/10.1007/s10182-008-0053-6

Download

Download PDF  'A Markov chain Monte Carlo algorithm for multiple imputation in large surveys'.
Preview
Content: Accepted Version
Filetype: PDF
Size: 1MB
View at publisher