A major concern with the Bayesian approach is the use of a unique probability measure to quantify all relevant uncertainty. Specifying a unique probability with extreme precision when only vague or fragmentary information is available may not be feasible. This would be less of a concern under a...

Standard tests and confidence sets in the moment inequality literature are not robust to model misspecification in the sense that they exhibit spurious precision when the identified set is empty. This paper introduces tests and confidence sets that provide correct asymptotic inference for a...

International rankings of countries based on inequality of opportunity indices may not be robust vis-à-vis the specific metric adopted to measure opportunities. Indices often aggregate relevant information and neglect to control for normatively irrelevant distributional factors. This paper...

[enter Abstract BThe marginal likelihood is the gold standard for Bayesian model comparison although it is well-known that the value of marginal likelihood could be sensitive to the choice of prior hyperparameters. Most models require computationally intense simulation-based methods to evaluate...

Dynamic mechanisms offer powerful techniques to improve on both revenue and efficiency by linking sequential auctions using state information, but these techniques rely on exact distributional information of the buyers' valuations (present and future), which limits their use in learning...

Research from the United States shows that gaps in early cognitive and non-cognitive ability appear early in the life cycle. Little is known about this important question for developing countries. This paper provides new evidence of sharp differences in cognitive development by socioeconomic...

The reliability of traditional asset pricing tests depends on: (1) correlations between asset returns and factors; (2) the time-series sample size T compared to the number of assets N. For macro-risk factors, like consumption growth, (1)-(2) are often such that traditional tests cannot be...

We study a canonical setting of learning in networks where initially agents receive conditionally i.i.d. signals about a binary state. The distribution according to which signals are drawn is called an information structure. Agents repeatedly communicate beliefs with their neighbors and update...

We study a robust version of the single-unit auction problem. The auctioneer has confidence in her estimate of the marginal distribution of a generic bidder's valuation, but does not have reliable information about the joint distribution. In this setting, we analyze the performance of...

This paper considers the estimation of dynamic causal effects using external instruments and a structural vector-autoregressive model with possibly non-stationary regressors. We provide general conditions under which the asymptotic normal approximation remains valid. In this case, the asymptotic...