A new document has been added to the Society for Political Methodology Website.
Title: Estimating Individual Causal Effects
Author(s): Patrick Lam
Entry Date: 2013-07-18
Keyword(s): causal inference
Abstract: Most current empirical work attempts to estimate average causal effects (ATE, ATT, etc.). Average effects are misleading because they do not apply to any specific observation and they obscure possible treatment effect heterogeneity. I argue that researchers should instead estimate individual causal effects (ICEs). To estimate ICEs, I develop a Bayesian model that incorporates matching and imputes missing potential outcomes. Once ICEs are estimated, any other causal estimand can be easily calculated. The model is flexible and can be extended to a variety of applications including binary and continuous treatments, various types of outcome variables, and two-stage analyses.
http://polmeth.wustl.edu/mediaDetail.php?docId=1407
**********************************************************
Political Methodology E-Mail List
Editors: Ethan Porter <[log in to unmask]>
Gregory Whitfield <[log in to unmask]>
**********************************************************
Send messages to [log in to unmask]
To join the list, cancel your subscription, or modify
your subscription settings visit:
http://polmeth.wustl.edu/polmeth.php
**********************************************************