| 线性混合模型用于艾滋病疗效预测和疗法选优 |
| |
| 引用本文： | 桂文林,韩兆洲.线性混合模型用于艾滋病疗效预测和疗法选优[J].数理统计与管理,2010,29(3). |
| |
| 作者姓名： | 桂文林 韩兆洲 |
| |
| 作者单位： | 1. 暨南大学统计系,广东,广州,510632;惠州学院数学系,广东,惠州,516007
2. 暨南大学统计系,广东,广州,510632 |
| |
| 摘 要： | 为探究线性混合效应模型在艾滋病疗效预测和疗法选优中的应用。利用美国艾滋病医疗试验机构ACTG的193A研究中的一组非平衡重复测量数据,以logcd4为体现疗效的因变量,年龄、性别为固定效应,建立截距和治疗时间的斜率随受试者随机变化且其期望值因疗法不同的线性混合效应模型,用SAS软件中mixed过程求解并预测。通过疗法对截距和治疗时间斜率期望值的影响选择最优疗法。结果表明模型有非常好的拟合和预测效果,疗法4为最优疗法。本研究为专业医生进行艾滋病疗效的预测和疗法选优提供了科学依据和方法。
|
| 关 键 词： | 艾滋病 混合效应模型 重复测量数据 |
Linear Mixed Effect Model for the AIDS Curative Effect Forecast and Optimal Treatment Choice |
| |
| GUI Wen-lin,HAN Zhao-zhou.Linear Mixed Effect Model for the AIDS Curative Effect Forecast and Optimal Treatment Choice[J].Application of Statistics and Management,2010,29(3). |
| |
| Authors: | GUI Wen-lin HAN Zhao-zhou |
| |
| Institution: | GUI Wen-lin~(1,2) HAN Zhao-zhou~1 (1.Statistics Department,Jinan University,Guangdong Guangzhou 510632,China,2.Mathematics Department Huizhou University,Guangdong Huizhou 516007,China) |
| |
| Abstract: | To inquiry linear mixed effect model in AIDS curative effect prediction and optimal treatment choice application.Using a group of non-equilibrium repeated measured data from the 193A study of ACTG,Logcd4 to reflect the curative effect of the dependent variable,age,gender as fixed effect,We establish linear mixed model intercept and slope of treatment time were randomly changed as subjects and their expectations are different for treatment methods.Then use the Proc-Mixed in SAS to forecast. Through the impac... |
| |
| Keywords: | AIDS mixed effect model repeated measure data |
| 本文献已被 CNKI 万方数据 等数据库收录！ |
|
