零膨胀Poisson分布模型回归分析
|
摘要
本文目的是介绍零膨胀Poisson分布模型回归分析。首先,介绍零膨胀计数资料及其零膨胀Poisson分布回归模型构建原理,包括"零膨胀Poisson分布回归模型的形式"和"零膨胀Poisson分布回归模型的求解";其次,介绍"零膨胀Poisson分布回归模型的SAS实现",包括"创建SAS数据集""呈现因变量Y的频数分布""求出因变量Y的均值和方差"和"基于全部自变量对因变量Y构建多重零膨胀Poisson分布回归模型"。本文结果提示,当计数资料为非严重过离散的零膨胀计数资料时,拟合"多重零膨胀Poisson分布回归模型",可获得满意的拟合效果。
The purpose of this paper was to introduce the regression analysis of the zero-inflated Poisson distribution model.Firstly,the concepts of the zero-inflated count data and the building principle of the zero-inflated Poisson distribution regression model were given,which included the following two aspects:(1)the form of the zero-inflated Poisson distribution regression model;(2)the solution for the model mentioned before. Secondly,the SAS realization of this kind of model for the zero-inflated count data was presented. The contents were as follows:(1)creating SAS data set;(2)displaying the frequency of the count dependent variable Y;(3)calculating the arithmetic mean and variance of the count dependent variable Y;(4) building a multiple zero-inflated Poisson distribution regression model based on all independent variables. The results of the article showed that the satisfaction of the fitted effects could be gotten by building the zero-inflated Poisson distribution regression model to the zero-inflated count data with the not severe over-dispersion.
The purpose of this paper was to introduce the regression analysis of the zero-inflated Poisson distribution model.Firstly,the concepts of the zero-inflated count data and the building principle of the zero-inflated Poisson distribution regression model were given,which included the following two aspects:(1)the form of the zero-inflated Poisson distribution regression model;(2)the solution for the model mentioned before. Secondly,the SAS realization of this kind of model for the zero-inflated count data was presented. The contents were as follows:(1)creating SAS data set;(2)displaying the frequency of the count dependent variable Y;(3)calculating the arithmetic mean and variance of the count dependent variable Y;(4) building a multiple zero-inflated Poisson distribution regression model based on all independent variables. The results of the article showed that the satisfaction of the fitted effects could be gotten by building the zero-inflated Poisson distribution regression model to the zero-inflated count data with the not severe over-dispersion.
引文
[1] SAS Institute Inc. STAT SAS 9. 3 User’s Guide[M]. Cary,NC:SAS Institute Inc,2011:2437-2548,2605-2804.
[2]胡良平.有限混合模型回归分析[J].四川精神卫生,2018,31(4):307-312.
[2]胡良平.有限混合模型回归分析[J].四川精神卫生,2018,31(4):307-312.