User Tools

Site Tools



This shows you the differences between two versions of the page.

Link to this comparison view

seminars:stat:181129 [2018/11/28 16:02]
qyu created
seminars:stat:181129 [2018/11/28 16:03] (current)
Line 1: Line 1:
 +<WRAP centeralign>##​Statistics Seminar##\\ Department of Mathematical Sciences</​WRAP>​
 +<WRAP 70% center>
 +^  **DATE:​**|Thursday,​ November 29, 2018 |
 +^  **TIME:​**|1:​15pm -- 2:15pm |
 +^  **LOCATION:​**|WH 100E |
 +^  **SPEAKER:​**|Qiqing Yu, Binghamton ​ University |
 +^  **TITLE:​**|The Proportional Hazards Model with Linearly Time-dependent Covariates and Interval-censored Data  |
 +<WRAP center box 80%>
 +<WRAP centeralign>​**Abstract**</​WRAP>​
 +The semi-parametric ​ estimation
 +under  the proportional hazards (PH) model with a linearly time-dependent
 +covariates and with interval-censored data has not been investigated before.
 +The partial likelihood approach does not work and one has to use the
 +generalized likelihood function (GLF).
 +There is a challenge in this problem.
 +The GLF must be  in the form of
 +the baseline hazard function, rather than the baseline survival function
 +as in the PH model with time-independent covariates,
 +and a feasible way to specify the hazard function is a piece-wise constant
 +function. However,
 +several naive ways do not yield a consistent estimator.
 +We propose proper modifications of the GLF.