Simulation-based Sensitivity Analysis for Non-ignorable Missing Data

There is no author summary for this article yet. Authors can add summaries to their articles on ScienceOpen to make them more accessible to a non-specialist audience.

Abstract

Sensitivity analysis is popular in dealing with missing data problems particularly for non-ignorable missingness. It analyses how sensitively the conclusions may depend on assumptions about missing data e.g. missing data mechanism (MDM). We called models under certain assumptions sensitivity models. To make sensitivity analysis useful in practice we need to define some simple and interpretable statistical quantities to assess the sensitivity models. However, the assessment is difficult when the missing data mechanism is missing not at random (MNAR). We propose a novel approach in this paper on attempting to investigate those assumptions based on the nearest-neighbour (KNN) distances of simulated datasets from various MNAR models. The method is generic and it has been applied successfully to several specific models in this paper including meta-analysis model with publication bias, analysis of incomplete longitudinal data and regression analysis with non-ignorable missing covariates.

Related collections

Most cited references 8

Record: found
Abstract: not found
Article: not found

The application of computers to taxonomy.

P H SNEATH (1957)

0 comments Cited 89 times – based on 0 reviews      Review now

Bookmark

Record: found
Abstract: found
Article: not found

Bayesian sensitivity analysis for unmeasured confounding in observational studies.

Paul Gustafson, Adrian Levy, Lawrence C McCandless (2007)

We consider Bayesian sensitivity analysis for unmeasured confounding in observational studies where the association between a binary exposure, binary response, measured confounders and a single binary unmeasured confounder can be formulated using logistic regression models. A model for unmeasured confounding is presented along with a family of prior distributions that model beliefs about a possible unknown unmeasured confounder. Simulation from the posterior distribution is accomplished using Markov chain Monte Carlo. Because the model for unmeasured confounding is not identifiable, standard large-sample theory for Bayesian analysis is not applicable. Consequently, the impact of different choices of prior distributions on the coverage probability of credible intervals is unknown. Using simulations, we investigate the coverage probability when averaged with respect to various distributions over the parameter space. The results indicate that credible intervals will have approximately nominal coverage probability, on average, when the prior distribution used for sensitivity analysis approximates the sampling distribution of model parameters in a hypothetical sequence of observational studies. We motivate the method in a study of the effectiveness of beta blocker therapy for treatment of heart failure. Copyright 2006 John Wiley & Sons, Ltd.