Year: 2005
Type: preprint
Abstract: :\nMultiple imputation is a method specifically designed for variance estimation in the presence of\nmissing data. Rubin’s combination formula requires that the imputation method is “proper” which\nessentially means that the imputations are random draws from a posterior distribution in a Bayesian\nframework. In national statistical institutes (NSI’s) like Statistics Norway, the methods used for\nimputing for nonresponse are typically non-Bayesian, e.g., some kind of stratified hot-deck. Hence,\nRubin’s method of multiple imputation is not valid and cannot be applied in NSI’s. This paper deals\nwith the problem of deriving an alternative combination formula that can be applied for imputation\nmethods typically used in NSI’s and suggests an approach for studying this problem. Alternative\ncombination formulas are derived for certain response mechanisms and hot-deck type imputation\nmethods.\nKeywords: Multiple imputation, survey sampling, nonresponse, hot-deck imputation
Author: Jan F. Bjørnstad
Language: English
Subfield: Statistics and Probability
Field: Mathematics
Domain: Physical Sciences
Open Access status: green
OpenAlex ID: W2467006870