Paper # Author Title
We study the nonparametric identification and estimation of a structural model for committee decisions. Members of a committee share a common information set, but differ in ideological bias while processing multiple information sources and in individual tastes while weighing multiple objectives. We consider two cases of the model where committee members have or don't have strategic incentives for making recommendations that conform with the committee decision. For both cases, pure-strategy Bayesian Nash equilibria exist, and we show how to use variations in the common information set to recover the distribution of members' private types from individual recommendation patterns. Building on the identification result, we estimate a structural model of interest rate decisions by the Monetary Policy Committee (MPC) at the Bank of England. We find some evidence that recommendations from external committee members are less distorted by strategic incentives than internal members. There is also evidence that MPC members differ more in their tastes for multiple objectives than in ideological bias. Download Paper
This paper studies entry and capacity decisions by dialysis providers in the U.S. We estimate a structural model where providers make strategic continuous choices of capacities based on private information about own costs and beliefs about competitors’ behaviors. We evaluate the impact on market structure and provider profits under counterfactual regulatory policies that increase per capacity cost or reduce per capacity payment. We find that these policies reduce the market capacity of dialysis stations. However, the downward sloping reaction curve shields some providers from negative profit shocks in certain markets. The paper also has a methodological contribution in that it proposes new estimators for Bayesian games with continuous actions, which differ qualitative from discrete Bayesian games such as those with binary entry decisions. Download Paper
Bidders’ risk attitudes have key implications for choices of revenue-maximizing auction formats. In ascending auctions, bid distributions do not provide information about risk preference. We infer risk attitudes using distributions of transaction prices and participation decisions in ascending auctions with entry costs. Nonparametric tests are proposed for two distinct scenarios: first, the expected entry cost can be consistently estimated from data; second, the data does not report entry costs but contains exogenous variations of potential competition and auction characteristics. In the first scenario, we exploit the fact that the risk premium required for entry - the difference between ex ante expected profits from entry and the certainty equivalent .is strictly positive if and only if bidders are risk averse. Our test is based on identification of bidders’ ex ante profits. In the second scenario, our test builds on the fact that risk attitudes affect how equilibrium entry probabilities vary with observed auction characteristics and potential competition. We also show identification of risk attitudes in a more general model of ascending auctions with selective entry, where bidders receive entry-stage signals that are correlated with private values. Download Paper
We introduce an approach for semi-parametric inference in dynamic binary choice models that does not impose distributional assumptions on the state variables unobserved by the econometrician. The proposed framework combines Bayesian inference with partial identification results. The method is applicable to models with finite space of observed states. We demonstrate the method on Rust's model of bus engine replacement. The estimation experiments show that the parametric assumptions about the distribution of the unobserved states can have a considerable effect on the estimates of per-period payoffs. At the same time, the effect of these assumptions on counterfactual conditional choice probabilities can be small for most of the observed states. Download Paper
We develop an empirical methodology to study markets for services. These markets are typically organized as multi-attribute auctions in which buyers take into account seller's price as well as various characteristics, including quality. Our identification and estimation strategies exploit observed buyers' and sellers' decisions to recover the distribution of sellers' qualities, the distribution of seller's costs conditional on quality, and the distribution of buyers' tastes. Our empirical results from the on-line market for programming services confirm that quality plays an important role. We use our estimates to study the effect of licensing restrictions and to assess the loss of value from using standard rather than multi-attribute auctions as is common in public procurement. Download Paper
We quantify the identifying power of special regressors in heteroskedastic binary regressions with median-independent or conditionally symmetric errors. We measure the identifying power using two criteria: the set of regressor values that help point identify coefficients in latent payoffs as in (Manski 1988); and the Fisher information of coefficients as in (Chamberlain 1986). We find for median-independent errors, requiring one of the regressors to be “special" (in a sense similar to (Lewbel 2000)) does not add to the identifying power or the information for coefficients. Nonetheless it does help identify the error distribution and the average structural function. For conditionally symmetric errors, the presence of a special regressor improves the identifying power by the criterion in (Manski 1988), and the Fisher information for coefficients is strictly positive under mild conditions. We propose a new estimator for coefficients that converges at the parametric rate under symmetric errors and a special regressor, and report its decent performance in small samples through simulations. Download Paper
We show nonparametric point identification of static binary games with incomplete information, using excluded regressors. An excluded regressor for player ¡ is a state variable that does not affect other players’ utility and is additively separable from other components in ¡’s payoff. When excluded regressors are conditionally independent from private information, the interaction effects between players and the marginal effects of excluded regressors on payoff are identified. In addition, if excluded regressors vary sufficiently relative to the support of private information, then the full payoff functions and the distribution of private information are also nonparametrically identified. We illustrate how excluded regressors satisfying these conditions arise in contexts such as entry games between firms, as variation in observed components of fixed costs. We extend our approach to accommodate the existence of multiple Bayesian Nash equilibria in the data-generating process without assuming equilibrium selection rules. For a semiparametric model with linear payoff, we propose root-N consistent and asymptotically normal estimators for parameters in players’payoffs. Download Paper
We introduce an approach for semiparametric inference in dynamic binary choice models that does not impose distributional assumptions on the state variables unobserved by the econometrician. The proposed framework combines Bayesian inference with partial identification results. The method is applicable to models with finite space for observed states. We demonstrate the method on Rust's model of bus engine replacement. The estimation experiments show that the parametric assumptions about the distribution of the unobserved states can have a considerable effect on the estimates of per-period payoffs. At the same time, the effect of these assumptions on counterfactual conditional choice probabilities can be small for most of the observed states. Download Paper
Bidders’ risk attitudes have important implications for sellers seeking to maximize expected revenues. In ascending auctions, auction theory predicts bid distributions in Bayesian Nash equilibrium does not convey any information about bidders' risk preference. We propose a new approach for inference of bidders’ risk attitudes when they make endogenous participation decisions. Our approach is based on the idea that bidders' risk premium -the difference between ex ante expected profits from entry and the certainty equivalent - required for entry into the auction is strictly positive if and only if bidders are risk averse. We show bidders' expected profits from entry into auctions is nonparametrically recoverable, if a researcher observes the distribution of transaction prices, bidders' entry decisions and some noisy measures of entry costs. We propose a nonparametric test which attains the correct level asymptotically under the null of risk-neutrality, and is consistent under fixed alternatives. We provide Monte Carlo evidence of the finite sample performance of the test. We also establish identification of risk attitudes in more general auction models, where in the entry stage bidders receive signals that are correlated with private values to be drawn in the bidding stage. Download Paper
Stochastic sequential bargaining models (Merlo and Wilson (1995, 1998)) have found wide applications in different fields including political economy and macroeconomics due to their flexibility in explaining delays in reaching an agreement. This paper presents new results in nonparametric identification and estimation of such models under different data scenarios. Download Paper
Stochastic sequential bargaining models (Merlo and Wilson (1995, 1998)) have found wide applications in different fields including political economy and macroeconomics due to their flexibility in explaining delays in reaching an agreement. This paper presents new results in nonparametric identification and estimation of such models under different data scenarios. Download Paper
This paper studies the inference of interaction effects (impacts of players' actions on each other's payoffs) in discrete simultaneous games with incomplete information. We propose an easily implementable test for the signs of state-dependent interaction effects that does not require parametric specifications of players' payoffs, the distributions of their private signals or the equilibrium selection mechanism. The test relies on the commonly invoked assumption that players' private signals are independent conditional on observed states. The procedure is valid in (but does not rely on) the presence of multiple equilibria in the data-generating process (DGP). As a by-product, we propose a formal test for multiple equilibria in the DGP.  We also show how to extend our arguments to identify signs of interaction effects when private signals are correlated. We provide Monte Carlo evidence of the test's good performance in finite samples. We then implement the test using data on radio programming of commercial breaks in the U.S., and infer stations' incentives to synchronize their commercial breaks. Our results support the earlier finding by Sweeting (2009) that stations have stronger incentives. Download Paper
This paper studies the inference of interaction effects, i.e., the impacts of players' actions on each other's payoffs, in discrete simultaneous games with incomplete information. We propose an easily implementable test for the signs of state-dependent interaction effects that does not require parametric specifications of players' payoffs, the distributions of their private signals or the equilibrium selection mechanism. The test relies on the commonly invoked assumption that players' private signals are independent conditional on observed states. The procedure is valid in the presence of multiple equilibria, and, as a by-product of our approach, we propose a formal test for multiple equilibria in the data-generating process.  We provide Monte Carlo evidence of the test's good performance infinite samples. We also implement the test to infer the direction of interaction effects in couples' joint retirement decisions using data from the Health and Retirement Study. Download Paper
This paper studies the inference of interaction effects, i.e., the impacts of players' actions on each other's payoffs, in discrete simultaneous games with incomplete information. We propose an easily implementable test for the signs of state-dependent interaction effects that does not require parametric specifications of players' payoffs, the distributions of their private signals or the equilibrium selection mechanism. The test relies on the commonly invoked assumption that players' private signals are independent conditional on observed states. The procedure is valid in the presence of multiple equilibria, and, as a by-product of our approach, we propose a formal test for multiple equilibria in the data-generating process.  We provide Monte Carlo evidence of the test's good performance in finite samples. We also implement the test to infer the direction of interaction effects in couples' joint retirement decisions using data from the Health and Retirement Study. Download Paper
Stochastic sequential bargaining games (Merlo and Wilson (1995, 1998)) have found wide applications in various fields including political economy and macroeconomics due to their flexibility in explaining delays in reaching an agreement. In this paper, we present new results in nonparametric identification of such models under different scenarios of data availability. First, we give conditions for an observed distribution of players decisions and agreed allocations of the surplus, or the "cake", to be rationalized by a sequential bargaining model. We show the common discount rate is identified, provided the surplus is monotonic in unobservable states (USV) given observed ones (OSV). Then the mapping from states to surplus, or the "cake function", is also recovered under appropriate normalizations. Second, when the cake is only observed under agreements, the discount rate and the impact of observable states on the cake can be identified, if the distribution of USV satisfies some exclusion restrictions and the cake is additively separable in OSV and USV. Third, if data only report when an agreement is reached but never report the size of the cake, we propose a simple algorithm that exploits shape restrictions on the cake function and the independence of USV to recover all rationalizable probabilities for agreements under counterfactual state transitions. Numerical examples show the set of rationalizable counterfactual outcomes so recovered can be informative. Download Paper
Stochastic sequential bargaining games (Merlo and Wilson (1995, 1998)) have found wide applications in various fields including political economy and macroeconomics due to their flexibility in explaining delays in reaching agreement. In this paper, we present new results in nonparametric identification of such models under different scenarios of data availability. First, with complete data on players decisions, the sizes of the surplus to be shared (cakes) and the agreed allocations, both the mapping from states to the total surplus (i.e. the "cake function") and the players common discount rate are identified, if the unobservable state variable (USV) is independent of observable ones (OSV), and the total surplus is strictly increasing in the USV conditional on the OSV. Second, when the cake size is only observed under agreements and is additively separable in OSV and USV, the contribution by OSV is identified provided the USV distribution satisfies some distributional exclusion restrictions. Third, if data only report when an agreement is reached but never report thecake sizes, we propose a simple algorithm that exploits exogenously given shape restrictions on the cake function and the independence of USV from OSV to recover all rationalizable probabilities for reaching an agreement under counterfactual state transitions. Numerical examples show the set of rationalizable counterfactual outcomes so recovered can be informative. Download Paper
I estimate a simultaneous discrete game with incomplete information where players’ private information are only required to be median independent of observed states and can be correlated with observable states. This median restriction is weaker than other assumptions on players’ private information in the literature (e.g. perfect knowledge of its distribution or its independence of the observable states). I show index coefficients in players’ utility functions are point-identified under an exclusion restriction and fairly weak conditions on the support of states. This identification strategy is fundamentally different from that in a single-agent binary response models with median restrictions, and does not involve any parametric assumption on equilibrium selection in the presence of multiple Bayesian Nash equilibria. I then propose a two-step extreme estimator for the linear coefficients, and prove its consistency. Download Paper
We address two issues in nonparametric structural analyses of dynamic binary choice processes (DBCP). First, the DBCP is not testable and decision makers’ single-period payoffs (SPP) cannot be identified even when the distribution of unobservable states (USV) is known. Numerical examples show setting SPP from one choice to arbitrary utility levels to identify that from the other can lead to errors in predicting choice probabilities under counterfactual state transitions. We propose two solutions. First, if a data generating process (DGP) has exogenous variations in observable state transitions, the DBCP becomes testable and SPP is identified. Second, exogenous economic restrictions on SPP (such as ranking of states by SPP, or shape restrictions) can be used to recover the identified set of rationalizable counterfactual choice probabilities (RCCP) that are consistent with model restrictions. The other (more challenging) motivating issue is that when the USV distribution is not known, misspecification of the distribution in structural estimation leads to errors in counterfactual predictions. We introduce a simple algorithm based on linear programming to recover sharp bounds on RCCP. This approach exploits the fact that some stochastic restrictions on USV (such as independence from observable states) and economic restrictions on SPP can be represented (without loss of information for counterfactual analyses) as linear restrictions on SPP and distributional parameters of USV. We use numerical examples to illustrate the algorithm and show sizes of identified sets of RCCP can be quite small relative to the outcome space. Download Paper
In this paper we study the identification and estimation of a class of binary regressions where conditional medians of additive disturbances are bounded between known or exogenously identified functions of regressors. This class includes several important microeconometric models, such as simultaneous discrete games with incomplete information, binary regressions with censored regressors, and binary regressions with interval data or measurement errors on regressors. We characterize the identification region of linear coefficients in this class of models and show how point-identification can be achieved in various microeconometric models under fairly general restrictions on structural primitives. We define a novel, two-step smooth extreme estimator, and prove its consistency for the identification region of coefficients. We also provide encouraging Monte Carlo evidence of the estimator’s performance in finite samples. Download Paper
In first-price auctions with interdependent bidder values, the distributions of private signals and values cannot be uniquely recovered from bids in Bayesian Nash equilibria. Non-identification invalidates structural analyses that rely on the exact knowledge of model primitives. In this paper I introduce tight, informative bounds on the distribution of revenues in counterfactual first-price and second-price auctions with binding reserve prices. These robust bounds are identified from distributions of equilibrium bids in first-price auctions under minimal restrictions where I allow for affiliated signals and both private and common-value paradigms. The bounds can be used to compare auction formats and to select optimal reserve prices. I propose consistent nonparametric estimators of the bounds. I extend the approach to account for observed heterogeneity across auctions, as well as binding reserve prices in the data. I use a recent data of 6,721 first-price auctions of U.S. municipal bonds to estimate bounds on counterfactual revenue distributions. I then bound optimal reserve prices for sellers with various risk attitudes. Download Paper