Barnhart H X, Kosinski A S, Sampson A R
Department of Biostatistics, Rollins School of Public Health of Emory University, Atlanta, GA 30322, USA.
Stat Med. 1999 Jan 30;18(2):199-211. doi: 10.1002/(sici)1097-0258(19990130)18:2<199::aid-sim1>3.0.co;2-e.
Multivariate random length data occur when we observe multiple measurements of a quantitative variable and the variable number of these measurements is also an observed outcome for each experimental unit. For example, for a patient with coronary artery disease, we may observe a number of lesions in that patient's coronary arteries, along with percentage of blockage of each lesion. Barnhart and Sampson first proposed the multiple population model to analyse multivariate random length data without covariates. This paper extends their approach to deal with multiple covariates. We propose a new multiple population regression model with covariates, and discuss the estimation issues. We analyse data from the TYPE II coronary intervention study to illustrate the methodology.
当我们对一个定量变量进行多次测量，且这些测量的变量数量也是每个实验单位的一个观测结果时，就会出现多变量随机长度数据。例如，对于一名冠心病患者，我们可能会观察到该患者冠状动脉中的一些病变，以及每个病变的阻塞百分比。巴恩哈特和桑普森首先提出了多总体模型，用于分析无协变量的多变量随机长度数据。本文扩展了他们的方法以处理多个协变量。我们提出了一种带有协变量的新的多总体回归模型，并讨论了估计问题。我们分析了来自II型冠状动脉介入研究的数据，以说明该方法。
