Bayesian sensitivity analysis of incomplete data: bridging pattern-mixture and selection models

Archived Abstract of Former PSC Researcher

Kaciroti, N., and Trivellore Raghunathan. 2014. "Bayesian sensitivity analysis of incomplete data: bridging pattern-mixture and selection models." Statistics in Medicine, 33(27): 4841-4857.

Pattern-mixture models (PMM) and selection models (SM) are alternative approaches for statistical analysis when faced with incomplete data and a nonignorable missing-data mechanism. Both models make empirically unverifiable assumptions and need additional constraints to identify the parameters. Here, we first introduce intuitive parameterizations to identify PMM for different types of outcome with distribution in the exponential family; then we translate these to their equivalent SM approach. This provides a unified framework for performing sensitivity analysis under either setting. These new parameterizations are transparent, easy-to-use, and provide dual interpretation from both the PMM and SM perspectives. A Bayesian approach is used to perform sensitivity analysis, deriving inferences using informative prior distributions on the sensitivity parameters. These models can be fitted using software that implements Gibbs sampling. Copyright (c) 2014 John Wiley & Sons, Ltd.

10.1002/sim.6302

Browse | Search | Next

PSC In The News

RSS Feed icon

Shaefer comments on the Cares Act impact in negating hardship during COVID-19 pandemic

Heller comments on lasting safety benefit of youth employment programs

More News

Highlights

Dean Yang's Combatting COVID-19 in Mozambique study releases Round 1 summary report

Help Establish Standard Data Collection Protocols for COVID-19 Research

More Highlights


Connect with PSC follow PSC on Twitter Like PSC on Facebook