James J. Heckman

Sample Selection Bias as a Specification Error

Sample selection bias as a specification error This paper discusses the bias that results from using non-randomly selected samples to estimate behavioral relationships as an ordinary specification error or «omitted variables» bias. A simple consistent two stage estimator is considered that enables analysts to utilize simple regression methods to estimate behavioral functions by least squares methods. The asymptotic distribution of the estimator is derived.

Matching As An Econometric Evaluation Estimator: Evidence from Evaluating a Job Training Programme

This paper considers whether it is possible to devise a nonexperimental procedure for evaluating a prototypical job training programme. Using rich nonexperimental data, we examine the performance of a two-stage evaluation methodology that (a) estimates the probability that a person participates in a programme and (b) uses the estimated probability in extensions of the classical method of matching. We decompose the conventional measure of programme evaluation bias into several components and find that bias due to selection on unobservables, commonly called selection bias in econometrics, is empirically less important than other components, although it is still a sizeable fraction of the estimated programme impact. Matching methods applied to comparison groups located in the same labour markets as participants and administered the same questionnaire eliminate much of the bias as conventionally measured, but the remaining bias is a considerable fraction of experimentally-determined programme impact estimates. We test and reject the identifying assumptions that justify the classical method of matching. We present a nonparametric conditional difference-in-differences extension of the method of matching that is consistent with the classical index-sufficient sample selection model and is not rejected by our tests of identifying assumptions. This estimator is effective in eliminating bias, especially when it is due to temporally-invariant omitted variables.

Matching as an Econometric Evaluation Estimator

This paper develops the method of matching as an econometric evaluation estimator. A rigorous distribution theory for kernel-based matching is presented. The method of matching is extended to more general conditions than the ones assumed in the statistical literature on the topic. We focus on the method of propensity score matching and show that it is not necessarily better, in the sense of reducing the variance of the resulting estimator, to use the propensity score method even if propensity score is known. We extend the statistical literature on the propensity score by considering the case when it is estimated both parametrically and nonparametrically. We examine the benefits of separability and exclusion restrictions in improving the efficiency of the estimator. Our methods also apply to the econometric selection bias estimator.

A METHOD FOR MINIMIZING THE IMPACT OF DISTRIBUTIONAL ASSUMPTIONS IN ECONOMETRIC MODELS FOR DURATION DATA

Conventional analyses of single spell duration models control for unobservables using a random effect estimator with the distribution of unobservables selected by ad hoc criteria. Both theoretical and empirical examples indicate that estimates of structural parameters obtained from conventional procedures are very sensitive to the choice of mixing distribution. Conventional procedures overparameterize duration models. We develop a consistent nonparametric maximum likelihood estimator for the distribution of unobservables and a computational strategy for implementing it. For a sample of unemployed workers our estimator produces estimates in concordance with standard search theory while conventional estimators do not. ECONOMIC THEORIES of search unemployment (Lippman and McCall [34]; Flinn and Heckman [14]), job turnover (Jovanovic [25]), mortality (Harris [17]), labor supply (Heckman and Willis [23]) and marital instability (Becker [3]) produce structural distributions for durations of occupancy of states. These theories generate qualitative predictions about the effects of changes in parameters on these structural distributions, and occasionally predict their functional forms.2 In order to test economic theories about durations and recover structural parameters, it is necessary to account for population variation in observed and unobserved variables unless it is assumed a priori that individuals are homogeneous.3 In every microeconomic study in which the hypothesis of heterogeneity is subject to test, it is not rejected. Temporally persistent unobserved components are an empirically important fact of life in microeconomic data (Heckman [19]). Since the appearance of papers by Silcock [39] and Blumen, Kogan, and McCarthy [5], social scientists have been aware that failure to adequately control for population heterogeneity can produce severe bias in structural estimates of duration models. Serious empirical analysts attempt to control for these unob

The Effects of Cognitive and Noncognitive Abilities on Labor Market Outcomes and Social Behavior

This article establishes that a low‐dimensional vector of cognitive and noncognitive skills explains a variety of labor market and behavioral outcomes. Our analysis addresses the problems of measurement error, imperfect proxies, and reverse causality that plague conventional studies. Noncognitive skills strongly influence schooling decisions and also affect wages, given schooling decisions. Schooling, employment, work experience, and choice of occupation are affected by latent noncognitive and cognitive skills. We show that the same low‐dimensional vector of abilities that explains schooling choices, wages, employment, work experience, and choice of occupation explains a wide variety of risky behaviors.

Dummy Endogenous Variables in a Simultaneous Equation System

This paper considers the formulation and estimation of simultaneous equation models with both discrete and continuous endogenous variables. The statistical model proposed here is sufficiently rich to encompass the classical simultaneous equation model for continuous endogenous variables and more recent models for purely discrete endogenous variables as special cases of a more general model.

Characterizing Selection Bias Using Experimental Data

This paper develops and applies semiparametric econometric methods to estimate the form of selection bias that arises from using nonexperimental comparison groups to evaluate social programs and to test the identifying assumptions that justify three widely-used classes of estimators and our extensions of them: (a) the method of matching; (b) the classical econometric selection model which represents the bias solely as a function of the probability of participation; and (c) the method of difference-in-differences. Using data from an experiment on a prototypical social program combined with unusually rich data from a nonexperimental comparison group, we reject the assumptions justifying matching and our extensions of that method but find evidence in support of the index-sufficient selection bias model and the assumptions that justify application of a conditional semiparametric version of the method of difference-in-difference. Fa comparable people and to appropriately weight participants and nonparticipants a sources of selection bias as conveniently measured. We present a rigorous defin bias and find that in our data it is a small component of conventially meausred it is still substantial when compared with experimentally-estimated program impa matching participants to comparison group members in the same labor market, givi same questionnaire, and making sure they have comparable characteristics substan the performance of any econometric program evaluation estimator. We show how t analysis to estimate the impact of treatment on the treated using ordinary obser

Skill Formation and the Economics of Investing in Disadvantaged Children

This paper summarizes evidence on the effects of early environments on child, adolescent, and adult achievement. Life cycle skill formation is a dynamic process in which early inputs strongly affect the productivity of later inputs.

Alternative methods for evaluating the impact of interventions: An overview

Abstract This paper presents methods for estimating the impact of training on earnings when non-random selection characterizes the enrollment of persons into training. We explore the benefits of cross-section, repeated cross-section and longitudinal data for addressing this problem by considering the assumptions required to use a variety of new and conventional estimators given access to various commonly encountered types of data. We investigate the plausibility of assumptions needed to justify econometric procedures when viewed in the light of prototypical decision rules determining enrollment into training. We examine the robustness of the estimators to choice-based sampling and contamination bias.

Choosing Among Alternative Nonexperimental Methods for Estimating the Impact of Social Programs: the Case of Manpower Training

The recent literature on evaluating manpower training programs demonstrates that alternative nonexperimental estimators of the same program produce a array of estimates of program impact. These findings have led to the call for experiments to be used to perform credible program evaluations. Missing in all of the recent pessimistic analyses of nonexperimental methods is any systematic discussion of how to choose among competing estimators. This paper explores the value of simple specification tests in selecting an appropriate nonexperimental estimator. A reanalysis of the National Supported Work Demonstration Data previously analyzed by proponents of social experiments reveals that a simple testing procedure eliminates the range of nonexperimental estimators that are at variance with the experimental estimates of program impact.