DIAGNOSTICS FOR MULTIPLE IMPUTATION BASED ON THE PROPENSITY SCORE

Simple item page
dc.contributor.advisorZhang, Guangyuen_US
dc.contributor.authorWang, Jiaen_US
dc.contributor.departmentEpidemiology and Biostatisticsen_US
dc.contributor.publisherDigital Repository at the University of Marylanden_US
dc.contributor.publisherUniversity of Maryland (College Park, Md.)en_US
dc.date.accessioned2010-07-03T05:37:07Z
dc.date.available2010-07-03T05:37:07Z
dc.date.issued2010en_US
dc.description.abstractMultiple imputation (MI) is a popular approach to handling missing data, however, there has been limited work on diagnostics of imputation results. We propose two diagnostic techniques for imputations based on the propensity score (1) compare the conditional distributions of observed and imputed values given the propensity score; (2) fit regression models of the imputed data as a function of the propensity score and the missing indicator. Simulation results show these diagnostic methods can identify the problems relating to the imputations given the missing at random assumption. We use 2002 US Natality public-use data to illustrate our method, where missing values in gestational age and in covariates are imputed using Sequential Regression Multiple Imputation method.en_US
dc.identifier.urihttp://hdl.handle.net/1903/10465
dc.subject.pqcontrolledHealth Sciences, Public Healthen_US
dc.subject.pquncontrolledDiagnosticsen_US
dc.subject.pquncontrolledMultiple imputationen_US
dc.subject.pquncontrolledPropensity scoreen_US
dc.titleDIAGNOSTICS FOR MULTIPLE IMPUTATION BASED ON THE PROPENSITY SCOREen_US
dc.typeThesisen_US

Files

Original bundle
Now showing 1 - 1 of 1
Thumbnail Image
Name:
Wang_umd_0117N_11323.pdf
Size:
3.55 MB
Format:
Adobe Portable Document Format
Download

Collections

UMD Theses and Dissertations
Epidemiology & Biostatistics Theses and Dissertations