PDF(88 KB)
PDF(88 KB)
PDF(88 KB)
具有不可忽略退出的面板数据混合半参数变系数模型
Mixtures of semiparametric varying coefficient models of panel data with nonignorable dropout
The analysis of panel data is frequently complicated by missing data due to information dropout. We assume that responses follow a semiparametric varying coefficient random effect model. The concept of two step estimation is used in order to provide consistent estimators of the parameteric and nonparametric parts. Themethods simplify the calculations and avoid the collinearity caused by more parameters in the model.
［1］HOGAN J W, LIN Xihong, HERMAN B. Mixtures of varying coefficient models for longitudinal data with discrete or continuous nonignorable dropout［J］. Biometrics, 2004, 60： 854-864.
［2］FAN Jianqing, ZHANG Jinting. Two step estimation of functional linear
models with application to longitudinal data［J］. Journal of the Royal Statistical Society: Series B, 2000, 62：303-322.
［3］王松桂， 史建红， 尹素菊， 等. 线性模型引论［M］. 北京:科学出版社， 2004.
［4］MCCULLOCH C E, SEARLE S R. Generalized, linear, and mixed models［M］. New York: John Wiley and Sons,Inc, 2001.
［5］茆诗松, 王静龙, 濮晓龙. 高等数理统计［M］. 北京:高等教育出版社, 2000.
［6］LIN Xihong, CARROL R J. Semiparametric regression for clustered data
using generalized estimating equation［J］. Journal of the American Statistical Association, 2001 ,96：1045-1056.
/
| 〈 |
|
〉 |
