DC Field | Value | Language |
---|---|---|
dc.contributor.author | Kim, Ji Young | ko |
dc.contributor.author | Kim, Jae Kwang | ko |
dc.date.accessioned | 2016-10-04T02:58:38Z | - |
dc.date.available | 2016-10-04T02:58:38Z | - |
dc.date.created | 2016-09-08 | - |
dc.date.created | 2016-09-08 | - |
dc.date.issued | 2012-09 | - |
dc.identifier.citation | JOURNAL OF THE KOREAN STATISTICAL SOCIETY, v.41, no.3, pp.291 - 303 | - |
dc.identifier.issn | 1226-3192 | - |
dc.identifier.uri | http://hdl.handle.net/10203/213009 | - |
dc.description.abstract | Parameter estimation with missing data is a frequently encountered problem in statistics. Imputation is often used to facilitate the parameter estimation by simply applying the complete-sample estimators to the imputed dataset. In this article, we consider the problem of parameter estimation with nonignorable missing data using the approach of parametric fractional imputation proposed by Kim (2011). Using the fractional weights, the E-step of the EM algorithm can be approximated by the weighted mean of the imputed data likelihood where the fractional weights are computed from the current value of the parameter estimates. Calibration fractional imputation is also considered as a way for improving the Monte Carlo approximation in the fractional imputation. Variance estimation is also discussed. Results from two simulation studies are presented to compare the proposed method with the existing methods. A real data example from the Korea Labor and Income Panel Survey (KLIPS) is also presented. (c) 2011 The Korean Statistical Society. Published by Elsevier B.V. All rights reserved | - |
dc.language | English | - |
dc.publisher | KOREAN STATISTICAL SOC | - |
dc.subject | GENERALIZED LINEAR-MODELS | - |
dc.subject | MULTIPLE-IMPUTATION | - |
dc.subject | INCOMPLETE DATA | - |
dc.subject | MIXTURE-MODELS | - |
dc.subject | EM ALGORITHM | - |
dc.subject | NONRESPONSE | - |
dc.title | Parametric fractional imputation for nonignorable missing data | - |
dc.type | Article | - |
dc.identifier.wosid | 000306717300002 | - |
dc.identifier.scopusid | 2-s2.0-84863102090 | - |
dc.type.rims | ART | - |
dc.citation.volume | 41 | - |
dc.citation.issue | 3 | - |
dc.citation.beginningpage | 291 | - |
dc.citation.endingpage | 303 | - |
dc.citation.publicationname | JOURNAL OF THE KOREAN STATISTICAL SOCIETY | - |
dc.identifier.doi | 10.1016/j.jkss.2011.10.022 | - |
dc.contributor.localauthor | Kim, Jae Kwang | - |
dc.contributor.nonIdAuthor | Kim, Ji Young | - |
dc.type.journalArticle | Article | - |
dc.subject.keywordAuthor | EM algorithm | - |
dc.subject.keywordAuthor | Monte Carlo EM | - |
dc.subject.keywordAuthor | Multiple imputation | - |
dc.subject.keywordAuthor | Not missing at random | - |
dc.subject.keywordPlus | GENERALIZED LINEAR-MODELS | - |
dc.subject.keywordPlus | MULTIPLE-IMPUTATION | - |
dc.subject.keywordPlus | INCOMPLETE DATA | - |
dc.subject.keywordPlus | MIXTURE-MODELS | - |
dc.subject.keywordPlus | EM ALGORITHM | - |
dc.subject.keywordPlus | NONRESPONSE | - |
Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.