Kaciroti Niko A, Raghunathan Trivellore
Center of Human Growth and Development, University of Michigan, Ann Arbor, MI, U.S.A.; Department of Biostatistics, University of Michigan, Ann Arbor, MI, U.S.A.
Stat Med. 2014 Nov 30;33(27):4841-57. doi: 10.1002/sim.6302. Epub 2014 Sep 24.
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.
模式混合模型（PMM）和选择模型（SM）是在面对不完整数据和不可忽略的缺失数据机制时进行统计分析的替代方法。这两种模型都做出了经验上无法验证的假设，并且需要额外的约束来识别参数。在此，我们首先引入直观的参数化方法来识别指数族分布中不同类型结果的PMM；然后将这些方法转化为等效的SM方法。这为在任何一种情况下进行敏感性分析提供了一个统一的框架。这些新的参数化方法是透明的、易于使用的，并且从PMM和SM两个角度提供了双重解释。使用贝叶斯方法进行敏感性分析，利用关于敏感性参数的信息先验分布得出推断。这些模型可以使用实现吉布斯抽样的软件进行拟合。
