| 主题： |
Semiparametric regression analysis of longitudinal skewed data |
| 类型： |
学术报告
|
| 主办方： |
|
| 报告人： |
林华珍（西南财经大学统计学院教授） |
| 日期： |
12月2日（星期2）上午9:00-10:00 |
| 地点： |
知新楼B-1248 |
| 内容： |
题目：Semiparametricregression analysis of longitudinal skewed data 报告人：林华珍（西南财经大学统计学院教授） 时间：12月2日（星期2）上午9:00-10:00 地点：知新楼B-1248 摘要：In this paper we develop a new semi-parametricregression model for longitudinal data. In the new model, we allow thetransformation function and the baseline function to be unknown. The proposed model can provide a much broaderclass of models than the existing additiveand multiple models. Our estimators for the regression parameters, thetransformation function and the baseline function are asymptotically normal,particularly, the estimators forregression parameters and the transformation function converge to their truevalues at the rate $n^{-1/2}$, the convergence rate that one could expect for aparametric model. In a simulation study, we demonstrate that the proposedsemiparametric method is robust with little loss of efficiency. Finally, weapply the new method to a study on longitudinal health care costs. |
