Multivariate matched proportions (MMP) data appears in a variety of contexts including post-market surveillance of adverse events in pharmaceuticals, disease classification, and agreement between care providers. It consists of multiple sets of paired binary measurements taken on the same subject. While recent work proposes non-Bayesian methods to address the complexities of MMP data, the issue of sparse response, where no or very few "yes" responses are recorded for one or more sets, is unaddressed. The presence of sparse response sets results in underestimates of variance, loss of coverage, and lowered power in existing methods. Bayesian methods have not previously been considered for MMP data but provide a useful framework when sparse responses are present. In particular, the Bayesian probit model provides an elegant solution to the problem of variance underestimation. We examine three approaches built on that model: a naive analysis with flat priors, a penalized analysis using half-Cauchy priors on the mean model variances, and a multivariate analysis with a Bayesian functional principal component analysis (FPCA) to model the latent covariance. We show that the multivariate analysis performs well on MMP data with sparse responses and outperforms existing non-Bayesian methods. In a re-analysis of data from a study of the system of care (SOC) framework for children with mental and behavioral disorders, we are able to provide a more complete picture of the relationships in the data. Our analysis provides additional insights into the functioning on the SOC that a previous univariate analysis missed.
翻译:多种不同比例(MMP)数据出现在多种情况下,包括药品、疾病分类和护理提供者之间协议的不利事件市场后监测,它包括在同一主题上采取的多套配对二进制测量方法。虽然最近的工作提出了非巴伊西亚方法来解决MMP数据的复杂性问题,但是没有记录任何或很少记录过“是”答复的松散反应问题没有得到解决。存在零散反应组合导致低估了差异、覆盖面丧失和现有方法中的权力下降。巴伊西亚方法以前没有考虑过MMP数据,但当反应少时提供了一个有用的框架。特别是,Bayesian probit模型为差异低估问题提供了优雅的解决办法。我们研究了基于该模型的三种方法:对平均模型差异进行天真分析,用半“是”答复进行惩罚性分析,以及用巴伊斯主要功能分析元分析(FCAFCA)进行多变分析以模拟潜在变差。我们显示,多变差分析在运行分析过程中对MMP系统进行了良好的分析,从目前的数据分析中提供了不甚可靠的数据分析。