Elie Tamer

Incomplete Simultaneous Discrete Response Model with Multiple Equilibria

A bivariate simultaneous discrete response model which is a stochastic representation of equilibria in a two-person discrete game is studied. The presence of multiple equilibria in the underlying discrete game maps into a region for the exogenous variables where the model predicts a nonunique outcome. This is an example of an incomplete econometric structure. Economists using this model have made simplifying assumptions to avoid multiplicity. I make a distinction between incoherent models and incomplete models, and then analyse the model in the presence of multiple equilibria, showing that the model contains enough information to identify the parameters of interest and to obtain a well defined semiparametric estimator. I also show that the latter is consistent and √n normal. Moreover, by exploiting the presence of multiplicity, one is able to obtain a more efficient estimator than the existing methods. Copyright 2003, Wiley-Blackwell.

Inference with an Incomplete Model of English Auctions

Standard models of English auctions abstract from actual practice by assuming that bidders continuously affirm their willingness to pay as the price rises exogenously. We show that one need not rely on these models to make useful inferences on the latent demand structure at private value English auctions. Weak implications of rational bidding provide sufficient structure to nonparametrically bound the distribution of bidder valuations and the optimal reserve price, based on observed bids. If auctions and/or bidders differ in observable characteristics, our approach also yields bounds on parameters characterizing the effects of observables on valuations. Whenever observed bids are consistent with the standard model, the identiÞed bounds collapse to the true distribution (or parameters) of interest. Throughout, we propose estimators that consistently estimate the identiÞed features. We conduct a number of Monte Carlo experiments and apply our methods to data from U.S. Forest Service timber auctions in order to assess reserve price policy.

Irregular Identification, Support Conditions, and Inverse Weight Estimation

In weighted moment condition models, we show a subtle link between identification and estimability that limits the practical usefulness of estimators based on these models. In particular, if it is necessary for (point) identification that the weights take arbitrarily large values, then the parameter of interest, though point identified, cannot be estimated at the regular (parametric) rate and is said to be irregularly identified. This rate depends on relative tail conditions and can be as slow in some examples as n−1/4. This nonstandard rate of convergence can lead to numerical instability and/or large standard errors. We examine two weighted model examples: (i) the binary response model under mean restriction introduced by Lewbel (1997) and further generalized to cover endogeneity and selection, where the estimator in this class of models is weighted by the density of a special regressor, and (ii) the treatment effect model under exogenous selection (Rosenbaum and Rubin (1983)), where the resulting estimator of the average treatment effect is one that is weighted by a variant of the propensity score. Without strong relative support conditions, these models, similar to well known “identified at infinity” models, lead to estimators that converge at slower than parametric rate, since essentially, to ensure point identification, one requires some variables to take values on sets with arbitrarily small probabilities, or thin sets. For the two models above, we derive some rates of convergence and propose that one conducts inference using rate adaptive procedures that are analogous to Andrews and Schafgans (1998) for the sample selection model.

Inference in censored models with endogenous regressors

This paper analyzes the linear regression model y = xb+e with a conditional median assumption Med( e | z)=0 where z is a vector of instruments. Added complication arises due to the censoring of the outcome y. We treat the censored model as a model with interval-observed outcome thus obtaining interval restrictions on conditional median regressions. This allows us to use the framework introduced by Manski and Tamer (2000) to analyze the information contained in these inequality restrictions. We first show identification of the parameter b in the absence of censoring and introduce a consistent estimator based on the minimum distance method. We then give conditions for global identification of b in the model above with censored y and endogenous x. We provide a consistent estimator that is based on a modified minimum distance method.

A simple estimator for nonlinear error in variable models

We propose a simple estimator for nonlinear method of moment models with measurement error of the classical type when no additional data, such as validation data or double measurements, are available. We assume that the marginal distributions of the measurement errors are Laplace (double exponential) with zero means and unknown variances and the measurement errors are independent of the latent variables and are independent of each other. Under these assumptions, we derive simple revised moment conditions in terms of the observed variables. They are used to make inference about the model parameters and the variance of the measurement error. The results of this paper show that the distributional assumption on the measurement errors can be used to point identify the parameters of interest. Our estimator is a parametric method of moments estimator that uses the revised moment conditions and hence is simple to compute. Our estimation method is particularly useful in situations where no additional data are available, which is the case in many economic data sets. Simulation study demonstrates good finite sample properties of our proposed estimator. We also examine the performance of the estimator in the case where the error distribution is misspecified.

The Identification Power of Equilibrium in Simple Games

We examine the identification power that (Nash) equilibrium assumptions play in conducting inference about parameters in some simple games. We focus on three static games in which we drop the Nash equilibrium assumption and instead use rationalizability as the basis for strategic play. The first example examines a bivariate discrete game with complete information of the kind studied in entry models. The second example considers the incomplete-information version of the discrete bivariate game. Finally, the third example considers a first-price auction with independent private values. In each example, we study the inferential question of what can be learned about the parameter of interest using a random sample of observations, under level-k rationality, where k is an integer ≥ 1. As k increases, our identified set shrinks, limiting to the identified set under full rationality or rationalizability (as k → ∞). This is related to the concepts of iterated dominance and higher-order beliefs, which are incorporated into the econometric analysis in our framework. We are then able to categorize what can be learned about the parameters in a model under various maintained levels of rationality, highlighting the roles of different assumptions. We provide constructive identification results that lead naturally to consistent estimators.

Sensitivity Analysis in Semiparametric Likelihood Models

We provide methods for inference on a finite dimensional parameter of interest, theta in Re^{d_theta}, in a semiparametric probability model when an infinite dimensional nuisance parameter, g, is present. We depart from the semiparametric literature in that we do not require that the pair (theta, g) is point identified and so we construct confidence regions for theta that are robust to non-point identification. This allows practitioners to examine the sensitivity of their estimates of theta to specification of g in a likelihood setup. To construct these confidence regions for theta, we invert a profiled sieve likelihood ratio (LR) statistic. We derive the asymptotic null distribution of this profiled sieve LR, which is nonstandard when theta is not point identified (but is chi^2 distributed under point identification). We show that a simple weighted bootstrap procedure consistently estimates this complicated distributions quantiles. Monte Carlo studies of a semiparametric dynamic binary response panel data model indicate that our weighted bootstrap procedures performs adequately in finite samples. We provide three empirical illustrations to contrast our procedure to the ones obtained using standard (less robust) methods.

Endogenous binary choice model with median restrictions

Abstract We propose an estimator for β in the binary choice model y=1[x′β+ϵ≥0] under the assumption that the median of the distribution of the unobserved random variable ϵ conditional on a vector of instruments z is zero. We provide sufficient conditions for point identification of the parameter β. We also provide a consistent estimator of β.

Bayesian inference in a class of partially identified models

This paper develops a Bayesian approach to inference in a class of partially identified econometric models. Models in this class are characterized by a known mapping between a point identified reduced‐form parameter μ and the identified set for a partially identified parameter θ. The approach maps posterior inference about μ to various posterior inference statements concerning the identified set for θ, without the specification of a prior for θ. Many posterior inference statements are considered, including the posterior probability that a particular parameter value (or a set of parameter values) is in the identified set. The approach applies also to functions of θ. The paper develops general results on large sample approximations, which illustrate how the posterior probabilities over the identified set are revised by the data, and establishes conditions under which the Bayesian credible sets also are valid frequentist confidence sets. The approach is computationally attractive even in high‐dimensional models, in that the approach avoids an exhaustive search over the parameter space. The performance of the approach is illustrated via Monte Carlo experiments and an empirical application to a binary entry game involving airlines.

Identification of Panel Data Models with Endogenous Censoring

This paper analyzes the identification question in censored panel data models, where the censoring can depend on both observable and unobservable variables in arbitrary ways. Under some general conditions, we derive the tightest sets on the parameter of interest. These sets (which can be singletons) represent the limit of what one can learn about the parameter of interest given the model and the data in that every parameter that belongs to these sets is observationally equivalent to the true parameter. We consider two separate sets of assumptions, motivated by the previous literature, each controlling for unobserved heterogeneity with an individual specific (fixed) effect. The first imposes a stationarity assumption on the unobserved disturbance terms, along the lines of Manski (1987), and Honore (1993). The second is a nonstationary model that imposes a conditional independence assumption. For both models, we provide sufficient conditions for these models to point identify the parameters. Since our identified sets are defined through parameters that obey first order dominance, we outline easily implementable approaches to build confidence regions based on recent advances in Linton et.al.(2010) on bootstrapping tests of stochastic dominance. We also extend our results to dynamic versions of the censored panel models in which we consider lagged observed, latent dependent variables and lagged censoring indicator variables as regressors.