The views expressed here are those of the individual authors and not necessarily those of the JSM sponsors, their officers, or their staff.
Online Program Home
Abstract Details
Activity Number:
|
312
|
Type:
|
Invited
|
Date/Time:
|
Tuesday, July 31, 2012 : 10:30 AM to 12:20 PM
|
Sponsor:
|
Council of Chapters
|
Abstract - #303753 |
Title:
|
Identification, Learning, and Less Informative Priors in Endogenous Variable Models
|
Author(s):
|
Justin L Tobias*+ and Josh Chan
|
Companies:
|
Purdue University and Australian National University
|
Address:
|
, Lafayette, IN, 47907, USA
|
Keywords:
|
Bayes ;
Endogeneity ;
Identification ;
MCMC
|
Abstract:
|
Estimation in models with endogeneity concerns begins by searching for instruments. This search is inherently subjective and formal identification of such models is generally achieved upon imposing the researcher's strong prior belief that such variables have no conditional impacts on the outcome variable. Results obtained from such analyses are necessarily conditioned upon the untestable opinions of the researcher, and such beliefs may not be widely shared.
In this paper we employ another Bayesian approach to estimation and inference in models with endogeneity concerns by imposing weaker prior assumptions than the dogmatic priors that are commonly used to exclude variables from the model. Doing so, however, requires working with a partially identified model. We introduce our prior, compare it to related methods introduced in recent work, and describe strategies for calculating marginal posteriors of interest. Our methods are also applied with generated data and in an application involving the impact of the Body Mass Index (BMI) on earnings
|
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 2012 program
|
2012 JSM Online Program Home
For information, contact jsm@amstat.org or phone (888) 231-3473.
If you have questions about the Continuing Education program, please contact the Education Department.