演講
1st
統 計 學 研 究 所
專 題 演 講
題 目: Kullback-Leibler Information for Model Selection and Comparison in
Logistic Linear Models
主講人: Dr. Guoqi Qian,
Department of Mathematics and Statistics, University of Melbourne, Australia
時 間: 96年12月7日（星期五）10：00 - 10：50
（上午10：50-11：10茶會於統計所821室舉行）
地 點: 清大綜合三館837室
Abstract
We consider two issues involved in model selection.
1. Model selection starts with a proposed model class, and it is often
unrealisticlly assumed that the true model generating the data belongs to
this model class. Then what would happen to model selection if the true
model is not in the proposed model class? In other words, how to quantify the
model selection bias in the situation of model class mis-specification?
2. Model selection often ends up with a selected optimum model minimizing or
maximizing a numeric selection criterion function. But it does not or is not
able to provide a measure of variability or uncertainty involved in model
selection. Such a measure, if available, would be very useful in determining
models which are indistinguishable from the optimum model.
We have developed new estimators of Kullback-Leibler information to address
these two issues. Our work will be presented in the context of logistic
regression model selection but can be extended to other model selection
problems.
敬請公佈 歡迎參加
2nd
清華大學、交通大學
統 計 學 研 究 所
專 題 演 講
題 目: Confidence intervals and confidence bands for the difference
of two median survival times
主講人: 張玉媚教授 (東海大學統計學系)
時 間: 96年12月7日（星期五）11：10 - 12：00
（上午10：50-11：10茶會於統計所821室舉行）
地 點: 清大綜合三館837室
Abstract
We are concerned with the estimation of the discrepancy between two
treatments when right-censored survival data are accompanied with covariates.
Conditional confidence intervals given the available covariates and
confidence bands over a certain region of covariates are constructed for the
difference between two median survival times under the unstratified and
stratified Cox proportional hazards models, respectively. The proposed
confidence intervals and confidence bands provide the information about the
difference in survivorship for patients with common covariates but in
different treatments. The results of the simulation study investigation of
the coverage probability and expected length of the confidence intervals and
bands suggest the one designed for the stratified Cox model when data fit
reasonably with the model. When the stratified Cox model is not feasible,
however, the one designed for the unstratified Cox model is recommended. The
use of the confidence intervals and confidence bands is finally illustrated
with a HIV+ data set.
敬請公佈 歡迎參加
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 140.113.114.185
※ 編輯: mangogogo 來自: 140.113.114.185 (12/07 09:29)
討論串 (同標題文章)