|
Activity Number:
|
581
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 6, 2009 : 10:30 AM to 12:20 PM
|
|
Sponsor:
|
ENAR
|
| Abstract - #303215 |
|
Title:
|
Targeted Maximum Likelihood Estimation of Individualized Treatment Rule Effects
|
|
Author(s):
|
Kelly Moore*+ and Mark J. van der Laan and Ira Tager and Romain Neugebauer
|
|
Companies:
|
University of California, Berkeley and University of California, Berkeley and University of California, Berkeley and University of California, Berkeley
|
|
Address:
|
Division of Biostatistics, School of Public Health, Berkeley, CA, 94704,
|
|
Keywords:
|
|
|
Abstract:
|
As an example, we consider the effect of decreases in ambient levels of ozone concentration on cardiac related mortalities in the Los Angeles Basin area. This effect is difficult to estimate using conventional approaches to causal inference that define this effect by comparing the mortality risks corresponding to hypothetical scenarios in which all geographical grids in the target population are exposed to a given level of ozone concentration. Such static treatments are highly unrealistic in this case since grids near coastal areas typically do not experience higher levels of ozone. We present targeted maximum likelihood estimators of realistic causal effects and illustrate them with the above application.
|
- The address information is for the authors that have a + after their name.
- Authors who are presenting talks have a * after their name.
Back to the full JSM 2009 program |
