基于纵向数据部分线性单指标模型的CD4细胞统计分析  

Statistical Analysis of CD4 Cells Based on Partial Linear Single Index Model of Longitudinal Data

作　　者：钱苏安 王从志 王清 燕善俊[1] QIAN Suan;WANG Congzhi;WANG Qing;YAN Shanjun(School of Mathematics and Physical Sciences,Xuzhou University of Technology,Xuzhou 221018,China)

机构地区：[1]徐州工程学院数学与物理科学学院,江苏徐州221018

出　　处：《现代信息科技》2020年第3期25-27,共3页Modern Information Technology

摘　　要：部分线性单指标模型是一类非常重要的半参数模型,它对于克服非参数统计中的维数灾难问题具有重要的理论价值。以该模型应用于HIV血清转换器中CD4细胞的统计推断,研究CD4细胞和SMOKE(通过香烟包测量的吸烟状况)、Year(自血清转换后的时间的影响)、PreCD4(感染前CD4细胞数)、年龄(相对于给定的时间来源)的关系。研究结果表明,CD4细胞和吸烟状况、血清转换的时间、年龄成正相关,与感染前细胞数成负相关。Partial linear single index model is a kind of very important semi parametric model,which has important theoretical value to overcome the dimension disaster in nonparametric statistics.The model is applied to the statistical inference of CD4 cells in HIV serum transducers to study the relationship between CD4 cells and SMOKE(smoking status measured by cigarette packs),Year(effect of time since serum conversion),PreCD4(number of CD4 cells before infection)and age(relative to a given time source).The results showed that CD4 cells were positively correlated with smoking status,time of serum conversion and age,and negatively correlated with the number of pre infection cells.

关 键 词：部分线性单指标模型 最小二乘法 CD4细胞 

分 类 号：O212.7[理学—概率论与数理统计]