论文部分内容阅读
目的 :研究医学重复观测数据的多变量随机系数模型 .方法 :对两种药物 (A药 :消瘾扶正胶囊 ,B药 :可乐宁 )治疗 12 0例患者后的舒张压和收缩压重复观测数据进行多变量随机系数模型分析 ,对模型系数的固定效应参数矩阵 ξ作最小二乘估计并进行组间比较 ,同时估计随机效应的方差 协方差矩阵 ,分析方法用SAS/IML软件编程得以实现 .结果 :得到了固定效应和随机效应有关参数的估计值 ,并给出了曲线图 .用药后患者的舒张压和收缩压随时间的变化而变化 ,且两个药物组曲线的变化趋势是不相同的 ,A药组的变化相对平缓 ,而B药组起伏波动较大 ,用药后A药组的舒张压和收缩压相对来说均较B药组为高 .结论 :多变量随机系数模型可有效地进行多变量重复观测数据的动态变化趋势分析以及随机效应分析 .
Objective: To study the multivariate random coefficient model of medical repeated observation data.Methods: The repeated observation data of diastolic blood pressure and systolic blood pressure after treatment of two kinds of drugs (A medicine: Huxian Fuzheng capsule and B medicine: Clonidine) Multivariate random coefficient model analysis, the model coefficient fixed effect parameter matrix ξ as the least squares estimation and comparison between groups, while estimating the variance random covariance matrix, the analysis method SAS / IML software programming can be achieved.Results : Estimates of fixed and random effects parameters are obtained and graphs are given. The diastolic and systolic pressures of patients after treatment vary with time, and the trends of the curves of the two drug groups are not the same , The change of A group was relatively gentle, while the fluctuation of B group was larger than that of B group.Conclusion: Multivariate random coefficient model can effectively Dynamic trend analysis and random effects analysis of multivariate repeated observations were performed.