Estimating Inverse-probability Weights for Longitudinal Data with Dropout or Truncation: The Xtrccipw Command. (June 2017)

• Record Type: Journal Article
• Authors: Daza, Eric J.; Hudgens, Michael G.; Herring, Amy H.
• Is Part Of: Stata journal. Volume 17:Number 2(2017)
• Page Start: 253
• Page End: 278
• Publication Date: 2017-06
• Subjects: st0474 -- xtrccipw -- dropout -- generalized estimating equations -- inverse-probability weights -- longitudinal data -- missing at random -- truncation -- weighted GEE; Statistics -- Periodicals; Statistics -- Computer programs -- Periodicals; 001.422
• DOI: 10.1177/1536867X1701700202
• Languages: English
• ISSNs: 1536-867X

Abstract

Individuals may drop out of a longitudinal study, rendering their outcomes unobserved but still well defined. However, they may also undergo truncation (for example, death), beyond which their outcomes are no longer meaningful. Kurland and Heagerty (2005, Biostatistics 6: 241–258) developed a method to conduct regression conditioning on nontruncation, that is, regression conditioning on continuation (RCC), for longitudinal outcomes that are monotonically missing at random (for example, because of dropout). This method first estimates the probability of dropout among continuing individuals to construct inverse-probability weights (IPWs), then fits generalized estimating equations (GEE) with these IPWs. In this article, we present thextrccipw command, which can both estimate the IPWs required by RCC and then use these IPWs in a GEE estimator by calling theglm command from withinxtrccipw . In the absence of truncation, thextrccipw command can also be used to run a weighted GEE analysis. We demonstrate thextrccipw command by analyzing an example dataset and the original Kurland and Heagerty (2005) data. We also usextrccipw to illustrate some empirical properties of RCC through a simulation study.