|
Activity Number:
|
556
- Causal Inference for Complex Data Challenges
|
|
Type:
|
Invited
|
|
Date/Time:
|
Thursday, August 6, 2020 : 3:00 PM to 4:50 PM
|
|
Sponsor:
|
SSC (Statistical Society of Canada)
|
|
Abstract #309232
|
|
|
Title:
|
Bayesian Approaches to Causal Inference: Some Comments on the Present Position and the Path Ahead
|
|
Author(s):
|
Paul Gustafson*
|
|
Companies:
|
University of British Columbia
|
|
Keywords:
|
Bayesian methods;
causal inference;
propensity scores
|
|
Abstract:
|
It seems uncontroversial to note that solving causal inference problems demands principled management of complex uncertainty structures. Likewise, the Bayesian approach to statistical inference offers principled management of complex uncertainty structures. Thus it seems surprising that Bayesian approaches lack prominence in the causal inference realm. This talk offers some comments on why this is, and whether and how the situation might change. One line of commentary addresses the foundational disconnect between Bayesian approaches and methods based on propensity scores. Another line addresses the level of parametric assumptions required in Bayesian tools for causal inference. The talk concludes with some speculation on interesting avenues of exploration going forward.
|
Authors who are presenting talks have a * after their name.
