Results 1  10
of
30
Nonparametric estimation of average treatment effects under exogeneity: a review
 REVIEW OF ECONOMICS AND STATISTICS
, 2004
"... Recently there has been a surge in econometric work focusing on estimating average treatment effects under various sets of assumptions. One strand of this literature has developed methods for estimating average treatment effects for a binary treatment under assumptions variously described as exogen ..."
Abstract

Cited by 597 (26 self)
 Add to MetaCart
Recently there has been a surge in econometric work focusing on estimating average treatment effects under various sets of assumptions. One strand of this literature has developed methods for estimating average treatment effects for a binary treatment under assumptions variously described as exogeneity, unconfoundedness, or selection on observables. The implication of these assumptions is that systematic (for example, average or distributional) differences in outcomes between treated and control units with the same values for the covariates are attributable to the treatment. Recent analysis has considered estimation and inference for average treatment effects under weaker assumptions than typical of the earlier literature by avoiding distributional and functionalform assumptions. Various methods of semiparametric estimation have been proposed, including estimating the unknown regression functions, matching, methods using the propensity score such as weighting and blocking, and combinations of these approaches. In this paper I review the state of this
Alternative Approaches to Evaluation in Empirical Microeconomics
, 2002
"... Four alternative but related approaches to empirical evaluation of policy interventions are studied: social experiments, natural experiments, matching methods, and instrumental variables. In each case the necessary assumptions and the data requirements are considered for estimation of a number of ke ..."
Abstract

Cited by 144 (1 self)
 Add to MetaCart
(Show Context)
Four alternative but related approaches to empirical evaluation of policy interventions are studied: social experiments, natural experiments, matching methods, and instrumental variables. In each case the necessary assumptions and the data requirements are considered for estimation of a number of key parameters of interest. These key parameters include the average treatment effect, the treatment of the treated and the local average treatment effect. Some issues of implementation and interpretation are discussed drawing on the labour market programme evaluation literature.
Efficient semiparametric estimation of quantile treatment effects
, 2003
"... This paper presents calculations of semiparametric efficiency bounds for quantile treatment effects parameters when selection to treatment is based on observable characteristics. The paper also presents three estimation procedures for these parameters, all of which have two steps: a nonparametric e ..."
Abstract

Cited by 120 (5 self)
 Add to MetaCart
This paper presents calculations of semiparametric efficiency bounds for quantile treatment effects parameters when selection to treatment is based on observable characteristics. The paper also presents three estimation procedures for these parameters, all of which have two steps: a nonparametric estimation and a computation of the difference between the solutions of two distinct minimization problems. RootN consistency, asymptotic normality, and the achievement of the semiparametric efficiency bound is shown for one of the three estimators. In the final part of the paper, an empirical application to a job training program reveals the importance of heterogeneous treatment effects, showing that for this program the effects are concentrated in the upper quantiles of the earnings distribution.
Inference on the Quantile Regression Process
, 2000
"... Tests based on the quantile regression process can be formulated like the classical KolmogorovSmirnov and CramervonMises tests of goodnessoffit employing the theory of Bessel processes as in?. However, it is frequently desirable to formulate hypotheses involving unknown nuisance parameters, the ..."
Abstract

Cited by 54 (2 self)
 Add to MetaCart
Tests based on the quantile regression process can be formulated like the classical KolmogorovSmirnov and CramervonMises tests of goodnessoffit employing the theory of Bessel processes as in?. However, it is frequently desirable to formulate hypotheses involving unknown nuisance parameters, thereby jeopardizing the distribution free character of these tests. We characterize this situation as "the Durbin problem" since it was posed in?, for parametric empirical processes. In this paper we consider an approach to the Durbin problem involving a martingale transformation of the parametric empirical process suggested by? and show that it can be adapted to a wide variety of inference problems involving the quantile regression process. In particular, we suggest new tests of the location shift and locationscale shift models that underlie much of classical econometric inference. The methods are illustrated in some limited MonteCarlo experiments and with a reanalysis of data on unemployment durations from the Pennsylvania Reemployment Bonus Experiments. The Pennsylvania experiments, conducted in 198889, were designed to test the efficacy of cash bonuses paid for early reemployment in shortening the duration of insured unemployment spells.
Nonparametric Tests for Treatment Effect Heterogeneity
 FORTHCOMING IN THE REVIEW OF ECONOMICS AND STATISTICS
, 2007
"... In this paper we develop two nonparametric tests of treatment effect heterogeneity. The first test is for the null hypothesis that the treatment has a zero average effect for all subpopulations defined by covariates. The second test is for the null hypothesis that the average effect conditional on t ..."
Abstract

Cited by 27 (6 self)
 Add to MetaCart
In this paper we develop two nonparametric tests of treatment effect heterogeneity. The first test is for the null hypothesis that the treatment has a zero average effect for all subpopulations defined by covariates. The second test is for the null hypothesis that the average effect conditional on the covariates is identical for all subpopulations, i.e., that there is no heterogeneity in average treatment effects by covariates. We derive tests that are straightforward to implement and illustrate the use of these tests on data from two sets of experimental evaluations of the effects of welfaretowork programs.
Doctors without Borders? Relicensing Requirements and Negative Selection in the Market for Physicians
 Journal of Labour Economics
, 2005
"... Relicensing requirements for professionals that move across borders are widespread. In this paper, we measure the effects of occupational licensing by exploiting an immigrant physician retraining assignment rule. Instrumental variables and quantile treatment effects estimates indicate large return ..."
Abstract

Cited by 13 (1 self)
 Add to MetaCart
Relicensing requirements for professionals that move across borders are widespread. In this paper, we measure the effects of occupational licensing by exploiting an immigrant physician retraining assignment rule. Instrumental variables and quantile treatment effects estimates indicate large returns to acquiring an occupational license and negative selection into licensing status. We also develop a model of optimal license acquisition which, together with the empirical results, suggests that stricter relicensing requirements may not only lead to practitioner rents, but also to lower average quality of service in the market for physicians. ∗We are grateful to the editor, Josh Angrist, and two anonymous referees for very useful com
On the predictive distributions of outcome gains in the presence of an unindentified parameter
 Journal of Business and Economic Statistics
, 2003
"... In this paper we describe methods for obtaining the predictive distributions of outcome gains in the framework of a standard latent variable selection model. While most previous work has focused on estimation of mean treatment parameters as the method for characterizing outcome gains from program pa ..."
Abstract

Cited by 12 (1 self)
 Add to MetaCart
In this paper we describe methods for obtaining the predictive distributions of outcome gains in the framework of a standard latent variable selection model. While most previous work has focused on estimation of mean treatment parameters as the method for characterizing outcome gains from program participation, we show how the entire distributions associated with these gains can be obtained in certain situations. Although the outofsample outcome gain distributions depend on an unidentified parameter, we use the results of Koop and Poirier (1997) to show that learning can take place about this parameter through information contained in the identified parameters via a positive definiteness restriction on the covariance matrix. In cases where this type of learning is not highly informative, the spread of the predictive distributions depends more critically on the prior. We show both theoretically and in extensive generated data experiments how learning takes place, and delineate the sensitivity of our results to the prior specifications. We relate our analysis to three treatment parameters widely used in the evaluation literature: (the Average Treatment Effect (ATE), the effect of Treatment on the Treated (TT), and the Local Average Treatment Effect (LATE)), and show how one might approach estimation of the predictive distributions associated with these outcome gains rather than simply the estimation of mean effects. We apply these techniques to predict the effect of literacy on the weekly wages of a sample of New Jersey child laborers in 1903.
Testing normality assumption in the sample selection model with application to travel demand
 Journal of Business and Economic Statistics
, 2003
"... In this paper we introduce a test for the normality assumption in the sample selection model. The test is based on a generalization of a seminonparametric maximum likelihood method. In this estimation method, the distribution of the error terms is approximated by a Hermite series, with normality as ..."
Abstract

Cited by 12 (0 self)
 Add to MetaCart
In this paper we introduce a test for the normality assumption in the sample selection model. The test is based on a generalization of a seminonparametric maximum likelihood method. In this estimation method, the distribution of the error terms is approximated by a Hermite series, with normality as a special case. Because all parameters of the model are estimated both under normality and in the more general specification, we can test for normality using the likelihood ratio approach. This test has reasonable power as is shown by a simulation study. Finally, we apply the generalized seminonparametric maximum likelihood estimation method and the normality test to a model of car ownership and car use. The assumption of normal distributed error terms is rejected and we provide estimates of the sample selection model that are consistent.
Semiparametric Estimation of Instrumental Variable Models for Causal Effects
, 1999
"... This article introduces a new class of instrumental variable (IV) estimators of causal treatment effects for linear and nonlinear models with covariates. The rationale for focusing on nonlinear models is to improve the approximation to the causal response function of interest. For example, if the de ..."
Abstract

Cited by 11 (2 self)
 Add to MetaCart
This article introduces a new class of instrumental variable (IV) estimators of causal treatment effects for linear and nonlinear models with covariates. The rationale for focusing on nonlinear models is to improve the approximation to the causal response function of interest. For example, if the dependent variable is binary or limited, or if the effect of the treatment is affected bycovariates, a nonlinear model is likely to be appropriate. However, identification is not attained through functional form restrictions. This paper shows how to estimate a welldefined approximation to a nonlinear causal response function of unknown functional form using simple parametric models. As an important special case, I introduce a linear model that provides the best linear approximation to an underlying causal relation. It is shown that Two Stage Least Squares (2SLS) does not always have this property and some possible interpretations of 2SLS coefficients are briefly studied. The ideas and estimators in th...