[演講公告] 6/4(五)統計所"兩場"專題演講
※ [本文轉錄自 NCTU-STAT97G 看板 #1C1X3zxN ]
作者: a5170040 (Piggy) 看板: NCTU-STAT97G
標題: [演講公告] 6/4(五)統計所"兩場"專題演講
時間: Wed Jun 2 16:06:18 2010
[第一場]
題 目：Another Look at Design of Blocked Fractional Factorial Split-Plot
Experiments
主講人：鄭清水教授(Department of Statistics,University of California,
Berkeley)
時 間：99年6月4日(星期五)上午10:00-10:50
(上午10:50-11:10茶會於交大統計所429室舉行)
地 點：交大綜合一館427室
Abstract
Design of blocked fractional factorial split-plot experiments was considered
by McLeod and Brewster (Technometrics, 2004). Split-plot designs arise,
e.g., when some treatment factors require larger experimental units than
others since their levels are more difficult to change. Blocking is needed
when the experimental runs cannot be conducted under homogeneous conditions.
In this talk, I will revisit this subject, and discuss the selection and
construction of blocked fractional factorial split-plot designs from a
different perspective.
[第二場]
題 目：Analysis of Current Status Data with Missing Covariates
主講人：溫啟仲教授(淡江大學數學系)
時 間：99年6月4日(星期五)上午11:10-12:00
(上午10:50-11:10茶會於交大統計所429室舉行)
地 點：交大綜合一館427室
Abstract
Statistical inference based on the right-censored data for proportional
hazard (PH) model with missing covariates has received considerable
attention, but interval-censored or current status data with missing
covariates are not yet investigated. Our study is partly motivated by
analysis of fracture data from a cross-sectional study, where the occurrence
time of fracture was interval-censored and covariate osteoporosis was not
reported for all residents. We assume that the data are realized from a PH
model. A nonparametric maximum likelihood estimation is proposed to analyze
current status data with missing covariates. Simulation and real data
analysis exhibit the nice performance of our proposal.
--
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 140.113.180.45
--
--
※ 發信站: 批踢踢實業坊(ptt.cc)
◆ From: 140.113.180.45