OPTIMAL LEARNING BY EXPERIMENTATIONThis paper analyses the dynamic decision problem of an agent who is initially uncertain as to the true shape of his payoff function, but who obtains information aboutit over time by observing the outcome of his past decisions.In the long run, the action is a short run optimum given the beliefs, but may not be an optimum for the true payoff function.We derive conditions under which the limit action is optimal for the true payoff function and establish the robustness of the results.Finally we study the adjustment process in an example where such complete learning does not achieve in the long run

An organization's promotion decision between two workers is modeled as a problem of boundedly rational learning about ability. The decisionmaker can bias noisy rank-order contests sequentially, thereby changing the information they convey. The optimal final-period bias favors the "leader," reinforcing his likely ability advantage. When optimally biased rank-order information is a sufficient statistic for cardinal information, the leader is favored in every period. In other environments, bias in early periods may (1) favor the early loser, (2) be optimal even when the workers are equally rated, and (3) reduce the favored worker's promotion chances.

This paper investigates the structures of strategy-proof mechanisms in general models of economies with pure public goods. Under the assumptions that the set of allocations is a subset of some finite-dimensional Euclidean space and that the admissible preferencees are continuous and convex, I establish that any strategy-proof mechanism is dictatorial whenever the decision problem is of more than one dimension. Furthermore, I establish a similar result when preference relations also satisfy the additional assumption of monotonicity. These results properly extend the Gibbard-Satterthwaite theorem to economies with pure public goods

Decisions made under ongoing uncertainty and costly reversibility entail a range of the state variable where inaction is optimal, which in turn produces hysteresis--permanent effects of temporary shifts. The range is usually defined by nonlinear equations that need numerical solutions. In this paper, a technique of analytical approximations is developed and applied to two models--menu costs and investment. The resulting explicit solutions help clarify why hysteresis is important even for small irreversibility. In the menu cost model, hysteresis is two orders of magnitude larger than under the Akerlof-Yellen or Mankiw assumptions

Identification conditions for binary choice errors-in-variables models are explored. Conditions for the consistency and asymptotic normality of the maximum likelihood estimators of binary choice models with unbounded explanatory variables are given. Two- or three-step estimators to simplify computation are also suggested.

We develop a model of repeated product improvements in a continuum of sectors. Each product follows a stochastic progression up a quality ladder.

This paper presents and implements statistical tests of stock-market forecastability and volatility that are immune from the severe statistical problems of earlier tests. It finds that although the null hypothesis of market efficiency is rejected, the rejections are only marginal. The paper also shows how volatility tests and recent regression tests are closely related, and demonstrates that when finite sample biases are taken into account, regression tests also fail to provide strong evidence of violations of the conventional valuation model

North-South trade is studied in a model of vertical product differentiation. The South produces a low-quality spectrum of goods and the North a high-quality spectrum. An increase in the South's population lowers its relative wage, expands the spectrum of Southern goods at the top, and shifts the Northern spectrum upward. An increase in Northern labour productivity raises its relative wage. If the increase is neutral or export-biased, then the South's terms of trade improve, the spectrum of Northern products expands, the spectrum of Southern products contracts, and the volume of trade grows. If it is biased against Northern exports, these effects are reversed. Similar results hold for neutral increases in Southern productivity.

Our subject is estimation and inference concerning long-run economic equilibria in models with stochastic trends. An asymptotic theory is provided to analyze a menu of currently existing estimators of cointegrated systems. We study in detail the single-equation ECM (SEECM) approach of Hendry. Our theoretical results lead to prescriptions for empirical work, such as specifying SEECM's nonlinearly and including lagged equilibrium relationships rather than lagged differences of the dependent variable as covariates. Simulations support these prescriptions, and point to problems of overfitting not encountered in the semiparametric approach of Phillips and Hansen (1990

Four foreign exchange spot rate series, recorded on an hourly basis for a six-month period in 1986 are examined. A seasonal GARCH model is developed to describe the time-dependent volatility apparent in the percentage nominal return of each currency. Hourly patterns in volatility are found to be remarkably similar across currencies and appear to be related to the opening and closing of the worlds major markets. Robust LM tests designed to deal with the extreme leptokurtosis in the data fails to uncover any evidence of misspecification or the presence of volatility spillover effects between the currencies or across markets.