{"title":"具有协变量缺失数据和聚类数据结构的倾向得分加权。","authors":"Xiao Liu","doi":"10.1080/00273171.2024.2307529","DOIUrl":null,"url":null,"abstract":"<p><p>Propensity score (PS) analyses are increasingly popular in behavioral sciences. Two issues often add complexities to PS analyses, including missing data in observed covariates and clustered data structure. In previous research, methods for conducting PS analyses with considering either issue alone were examined. In practice, the two issues often co-occur; but the performance of methods for PS analyses in the presence of both issues has not been evaluated previously. In this study, we consider PS weighting analysis when data are clustered and observed covariates have missing values. A simulation study is conducted to evaluate the performance of different missing data handling methods (complete-case, single-level imputation, or multilevel imputation) combined with different multilevel PS weighting methods (fixed- or random-effects PS models, inverse-propensity-weighting or the clustered weighting, weighted single-level or multilevel outcome models). The results suggest that the bias in average treatment effect estimation can be reduced, by better accounting for clustering in both the missing data handling stage (such as with the multilevel imputation) and the PS analysis stage (such as with the fixed-effects PS model, clustered weighting, and weighted multilevel outcome model). A real-data example is provided for illustration.</p>","PeriodicalId":53155,"journal":{"name":"Multivariate Behavioral Research","volume":" ","pages":"411-433"},"PeriodicalIF":5.3000,"publicationDate":"2024-05-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"Propensity Score Weighting with Missing Data on Covariates and Clustered Data Structure.\",\"authors\":\"Xiao Liu\",\"doi\":\"10.1080/00273171.2024.2307529\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<p><p>Propensity score (PS) analyses are increasingly popular in behavioral sciences. Two issues often add complexities to PS analyses, including missing data in observed covariates and clustered data structure. In previous research, methods for conducting PS analyses with considering either issue alone were examined. In practice, the two issues often co-occur; but the performance of methods for PS analyses in the presence of both issues has not been evaluated previously. In this study, we consider PS weighting analysis when data are clustered and observed covariates have missing values. A simulation study is conducted to evaluate the performance of different missing data handling methods (complete-case, single-level imputation, or multilevel imputation) combined with different multilevel PS weighting methods (fixed- or random-effects PS models, inverse-propensity-weighting or the clustered weighting, weighted single-level or multilevel outcome models). The results suggest that the bias in average treatment effect estimation can be reduced, by better accounting for clustering in both the missing data handling stage (such as with the multilevel imputation) and the PS analysis stage (such as with the fixed-effects PS model, clustered weighting, and weighted multilevel outcome model). A real-data example is provided for illustration.</p>\",\"PeriodicalId\":53155,\"journal\":{\"name\":\"Multivariate Behavioral Research\",\"volume\":\" \",\"pages\":\"411-433\"},\"PeriodicalIF\":5.3000,\"publicationDate\":\"2024-05-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Multivariate Behavioral Research\",\"FirstCategoryId\":\"102\",\"ListUrlMain\":\"https://doi.org/10.1080/00273171.2024.2307529\",\"RegionNum\":3,\"RegionCategory\":\"心理学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"2024/2/20 0:00:00\",\"PubModel\":\"Epub\",\"JCR\":\"Q1\",\"JCRName\":\"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Multivariate Behavioral Research","FirstCategoryId":"102","ListUrlMain":"https://doi.org/10.1080/00273171.2024.2307529","RegionNum":3,"RegionCategory":"心理学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"2024/2/20 0:00:00","PubModel":"Epub","JCR":"Q1","JCRName":"MATHEMATICS, INTERDISCIPLINARY APPLICATIONS","Score":null,"Total":0}
Propensity Score Weighting with Missing Data on Covariates and Clustered Data Structure.
Propensity score (PS) analyses are increasingly popular in behavioral sciences. Two issues often add complexities to PS analyses, including missing data in observed covariates and clustered data structure. In previous research, methods for conducting PS analyses with considering either issue alone were examined. In practice, the two issues often co-occur; but the performance of methods for PS analyses in the presence of both issues has not been evaluated previously. In this study, we consider PS weighting analysis when data are clustered and observed covariates have missing values. A simulation study is conducted to evaluate the performance of different missing data handling methods (complete-case, single-level imputation, or multilevel imputation) combined with different multilevel PS weighting methods (fixed- or random-effects PS models, inverse-propensity-weighting or the clustered weighting, weighted single-level or multilevel outcome models). The results suggest that the bias in average treatment effect estimation can be reduced, by better accounting for clustering in both the missing data handling stage (such as with the multilevel imputation) and the PS analysis stage (such as with the fixed-effects PS model, clustered weighting, and weighted multilevel outcome model). A real-data example is provided for illustration.
期刊介绍:
Multivariate Behavioral Research (MBR) publishes a variety of substantive, methodological, and theoretical articles in all areas of the social and behavioral sciences. Most MBR articles fall into one of two categories. Substantive articles report on applications of sophisticated multivariate research methods to study topics of substantive interest in personality, health, intelligence, industrial/organizational, and other behavioral science areas. Methodological articles present and/or evaluate new developments in multivariate methods, or address methodological issues in current research. We also encourage submission of integrative articles related to pedagogy involving multivariate research methods, and to historical treatments of interest and relevance to multivariate research methods.