Regression models for mixed Poisson and continuous longitudinal data
Regression models for mixed Poisson and continuous longitudinal data
复制标题
DOI：
10.1002/sim.2776
复制
发表时间：
2007-09-10
影响因子：
2
通讯作者：
Zhang, He
中科院分区：
文献类型：
--
作者：
Yang, Ying;Kang, Han;Zhang, He
在这篇文章中，我们开发灵活的回归模型，在两个方面来评估的协变量对混合泊松和连续响应的影响，并评估如何泊松响应和连续响应之间的相关性随时间的变化。提出了当存在随时间变化的非均匀方差和相关性时处理混合连续和泊松响应的回归模型的方案。我们的一般方法是首先联合建立边际模型，并通过似然比检验来检查方差和相关性是否随时间变化。如果方差和相关性随时间变化，我们将进行适当的数据转换，以正确评估协变量对混合响应的影响。将所提出的方法应用于间质性膀胱炎数据库（ICDB）队列研究，我们发现正相关性随时间显著变化，这表明在建模和推断中不应忽视异质性方差。版权所有（c）2006约翰威利父子有限公司。
In this article we develop flexible regression models in two respects to evaluate the influence of the covariate variables on the mixed Poisson and continuous responses and to evaluate how the correlation between Poisson response and continuous response changes over time. A scenario for dealing with regression models of mixed continuous and Poisson responses when the heterogeneous variance and correlation changing over time exist is proposed. Our general approach is first to jointly build marginal model and to check whether the variance and correlation change over time via likelihood ratio test. If the variance and correlation change over time, we will do a suitable data transformation to properly evaluate the influence of the covariates on the mixed responses. The proposed methods are applied to the interstitial cystitis data base (ICDB) cohort study, and we find that the positive correlations significantly change over time, which suggests heterogeneous variances should not be ignored in modelling and inference. Copyright (c) 2006 John Wiley & Sons, Ltd.