Lectures
Location Home > Research > Lectures > Content
Estimating causal effects arising from a treatment sequence
编辑:林煜发布时间:2019年01月17日

Speaker:Xiaoqin Wang(University of Gävle

Time:2019-01-17 9:00

Location:Conference Room 108 at Experiment Building at Haiyun Campus

Abstract: In economic medical practices, a sequence of treatments are assigned to influence an outcome of interest that occurs after the last treatment. Between treatments, there exist time-dependent covariates that may be influenced by the earlier treatments at the same time confounders of the subsequent treatments. The causal effects of interest are the net effects of individual treatments the causal effect of a posited treatment regime on the outcome after the last treatment. In this seminar, we will first review the well-known difficulties of estimating these causal effects then introduce a method of estimating these causal effects that can avoid the known difficulties.

Main references:

(1)   WANG, X. YIN, L. (2015). Identifying estimating net effects of treatments in sequential causal inference. Electron. J. Stat. 9 1608–1643. MR3379004

(2)   Wang, X. Yin, L. (2019) new g-formula for the sequential causal effect blip effect of treatment in sequential causal inference. To appear in Annals of Statistics.

Speaker Introduction:

EDUCATION: Xiamen University, Bachelor Degree of Science, 1982-07, Mathematics

Xiamen University, Degree of Science, 1985-07, Mathematics

Uppsala University, Degree of Doctor of Philosophy, 1990-05, Mathematics

PREVIOUS CURRENT POSITIONS:

Lecturer (universitetslektor) ,Department of Mathematics, Uppsala University,1990. 7 – 1994.6

Senior Lecturer,  Associate Professor, statistics,  University of Gävle,  1994 07 –

Researcher,     Department of Medical Epidemiology Biostatistics,   Karolinska Institute 1998 01--1998 07



Baidu
sogou