Modeling and calculating the effect of treatment at baseline from panel outcomes.

We propose and examine a panel data model for isolating the effect of a treatment, taken once at baseline, from outcomes observed over subsequent time periods. In the model, the treatment intake and outcomes are assumed to be correlated, due to unobserved or unmeasured confounders. Intake is partly determined by a set of instrumental variables and the confounding on unobservables is modeled in a flexible way, varying both by time and treatment state. Covariate effects are assumed to be subject-specific and potentially correlated with other covariates. Estimation and inference is by Bayesian methods that are implemented by tuned Markov chain Monte Carlo methods. Because our analysis is based on the framework developed by Chib [2004. Analysis of treatment response data without the joint distribution of counterfactuals. Journal of Econometrics, in press], the modeling and estimation does not involve either the unknowable joint distribution of the potential outcomes or the missing counterfactuals. The problem of model choice through marginal likelihoods and Bayes factors is also considered. The methods are illustrated in simulation experiments and in an application dealing with the effect of participation in high school athletics on future labor market earnings.

[1]  D. Rubin,et al.  Assessing the effect of an influenza vaccine in an encouragement design. , 2000, Biostatistics.

[2]  Siddhartha Chib,et al.  Analysis of treatment response data without the joint distribution of potential outcomes , 2007 .

[3]  G. Becker,et al.  A Theory of the Allocation of Time , 1965 .

[4]  D. Rubin,et al.  Bayesian inference for causal effects in randomized experiments with noncompliance , 1997 .

[5]  Siddhartha Chib,et al.  Semiparametric Bayes analysis of longitudinal data treatment models , 2002 .

[6]  Siddhartha Chib,et al.  MARKOV CHAIN MONTE CARLO METHODS: COMPUTATION AND INFERENCE , 2001 .

[7]  John M. Olin.  On MCMC sampling in hierarchical longitudinal models , 1999 .

[8]  Lung-fei Lee.  Unionism and Wage Rates: A Simultaneous Equations Model with Qualitative and Limited Dependent Variables , 1978 .

[9]  S. Chib,et al.  Bayes inference in regression models with ARMA (p, q) errors , 1994 .

[10]  John M. Barron,et al.  The Effects of High School Athletic Participation on Education and Labor Market Outcomes , 2000, Review of Economics and Statistics.

[11]  S. Chib,et al.  Understanding the Metropolis-Hastings Algorithm , 1995 .

[12]  Justin L. Tobias,et al.  Do Dropouts Suffer from Dropping Out? Estimation and Prediction of Outcome Gains in Generalized Selection Models , 2004 .

[13]  David Card.  The Causal Effect of Education on Learning , 1999 .

[14]  S. Chib.  Marginal Likelihood from the Gibbs Output , 1995 .

[15]  S. Chib,et al.  Bayesian analysis of binary and polychotomous response data , 1993 .

[16]  S. Chib,et al.  Marginal Likelihood From the Metropolis–Hastings Output , 2001 .

[17]  R. Little,et al.  Inference for the Complier-Average Causal Effect From Longitudinal Data Subject to Noncompliance and Missing Data, With Application to a Job Training Assessment for the Unemployed , 2001 .