Instrumental variables are widely used in applied econometrics to achieve identification and carry out estimation and inference in models that contain endogenous explanatory variables. In most applications, the function of interest (e.g., an Engel curve or demand function) is assumed to be known up to finitely many parameters (e.g., a linear model), and instrumental variables are used identify and estimate these parameters. However, linear and other finite-dimensional parametric models make strong assumptions about the population being modeled that are rarely if ever justified by economic theory or other a priori reasoning and can lead to seriously erroneous conclusions if they are incorrect. This paper explores what can be learned when the function of interest is identified through an instrumental variable but is not assumed to be known up to finitely many parameters. The paper explains the differences between parametric and nonparametric estimators that are important for applied research, describes an easily implemented nonparametric instrumental variables estimator, and presents empirical examples in which nonparametric methods lead to substantive conclusions that are quite different from those obtained using standard, parametric estimators.

This paper is concerned with inference about a function g that is identified by a conditional moment restriction involving instrumental variables. The paper presents a test of the hypothesis that g belongs to a finite-dimensional parametric family against a nonparametric alternative. The test does not require nonparametric estimation of g and is not subject to the ill-posed inverse problem of nonparametric instrumental variables estimation. Under mild conditions, the test is consistent against any alternative model. In large samples, its power is arbitrarily close to 1 uniformly over a class of alternatives whose distance from the null hypothesis is O(n−1/2), where n is the sample size. In Monte Carlo simulations, the finite-sample power of the new test exceeds that of existing tests.

The block bootstrap is the best known bootstrap method for time-series data when the analyst does not have a parametric model that reduces the data generation process to simple random sampling. However, the errors made by the block bootstrap converge to zero only slightly faster than those made by first-order asymptotic approximations. This paper describes a bootstrap procedure for data that are generated by a Markov process or a process that can be approximated by a Markov process with sufficient accuracy. The procedure is based on estimating the Markov transition density nonparametrically. Bootstrap samples are obtained by sampling the process implied by the estimated transition density. Conditions are given under which the errors made by the Markov bootstrap converge to zero more rapidly than those made by the block bootstrap.

The proportional hazard model with unobserved heterogeneity gives the hazard function of a random variable conditional on covariates and a second random variable representing unobserved heterogeneity. This paper shows how to estimate the baseline hazard function and the distribution of the unobserved heterogeneity nonparametrically. The baseline hazard function and heterogeneity distribution are assumed to satisfy smoothness conditions but are not assumed to belong to known, finite-dimensional, parametric families. Existing estimators assume that the baseline hazard function or heterogeneity distribution belongs to a known parametric family. Thus, the estimators presented here are more general than existing ones.

The least-absolute-deviations (LAD) estimator for a median-regression model does not satisfy the standard conditions for obtaining asymptotic refinements through use of the bootstrap because the LAD objective function is not smooth. This paper overcomes this problem by smoothing the objective function. The smoothed estimator is asymptotically equivalent to the standard LAD estimator. With bootstrap critical values, the rejection probabilities of symmetrical t and X 2 tests based on the smoothed estimator are correct through O(n -γ ) under the null hypothesis, where γ<1 but can be arbitrarily close to 1. In contrast, first-order asymptotic approximations make errors of size O(n -γ ). These results also hold for symmetrical t and X 2 tests for censored median regression models.

This paper shows how to estimate a model in which an unknown transformation of the dependent variable is a linear function of explanatory variables plus an unobserved random variable, U, whose distribution is unknown. The model nests many familiar parametric and semiparametric models, including models with Box-Cox transformed dependent variables and proportional hazards models with and without unobserved heterogeneity. The paper develops root-n consistent, asymptotically normal estimators of the transformation function, coefficients of the explanatory variables, and distribution of U. The results of Monte Carlo experiments indicate that the estimators work well in samples of size one hundred. Copyright 1996 by The Econometric Society.

This paper describes a semiparametric estimator for binary response models in which there may be arbitrary heteroskedasticity of unknown form. The estimator is obtained by maximizing a smoothed version of the objective function of C. Manski's maximum score estimator. The smoothing procedure is similar to that used in kernel nonparametric density estimation. The resulting estimator's rate of convergence in probability is the fastest possible under the assumptions that are made. The centered, normalized estimator is asymptotically normally distributed. Methods are given for consistently estimating the parameters of the limiting distribution and for selecting the bandwidth required by the smoothing procedure. Copyright 1992 by The Econometric Society.

This paper presents a test for exogeneity of explanatory variables that minimizes the need for auxiliary assumptions that are not required by the definition of exogeneity. It concerns inference about a non-parametric function g that is identified by a conditional moment restriction involving instrumental variables (IV). A test of the hypothesis that g is the mean of a random variable Y conditional on a covariate X is developed that is not subject to the ill-posed inverse problem of non-parametric IV estimation. The test is consistent whenever g differs from E (Y ∣ X) on a set of non-zero probability. The usefulness of this new exogeneity test is displayed through Monte Carlo experiments and an application to estimation of non-parametric consumer expansion paths.

Linear models with error components are widely used to analyse panel data. Some applications of these models require knowledge of the probability densities of the error components. Existing methods handle this requirement by assuming that the densities belong to known parametric families of distributions (typically the normal distribution). This paper shows how to carry out nonparametric estimation of the densities of the error components, thereby avoiding the assumption that the densities belong to known parametric families. The nonparametric estimators are applied to an earnings model using data from the Current Population Survey. The model's transitory error component is not normally distributed. Use of the nonparametric density estimators yields estimates of the probability that individuals with low earnings will become high earners in the future that are much lower than the estimates obtained under the assumption of normally distributed error components.