[Macroeconomic models with rational expectations find a new justification if these models appear as limits of some learning procedures. In this paper we consider the case in which, during the learning period, the predictions are obtained by regression. We exhibit the necessary and sufficient condition on the parameter of the model ensuring the convergence of the learning process. The limit is the solution of a rational expectations model in which the information set only includes the exogenous variables used in the auxiliary regression.]

Ce modele est principalement utilise en analyse input-output: A represente alors les echanges interindustriels de l'annee de base, u et v les consommations intermediaires totales par produit et par branche de l'annee de projection; plus generalement on peut appliquer cette methode pour desagreger des projections globales de flux positifs (importations par pays et produit, flux de transports . . ) lorsque l'on suppose une certaine stabilite structurelle. Diverses interpretations economiques des coefficients r, et s1 (qui sont en fait strictement positifs puisque u, et v; le sont aussi) ont ete avancees;1 notons toutefois que les grandeurs absolues de r et s n'ont pas de signification intrinseque, car si (r, s) est

The problems associated with interpersonal comparisons are particularly intractable. This paper presents a procedure whereby the relative importance of any particular individual varies over the set of social states. In one sense, the stronger (relative to some norm) a person feels about any particular pairwise decision, the larger his say in that outcome. This procedure leads to a nested sequence of aggregate partial orderings which reflects this strength of preference. Under the assumptions presented it is also possible, given any two social states, to characterize the minimal amount of interpersonal comparison which is necessary in order to arrive at an aggregate ordering.

This paper evaluates the effectiveness of four econometric approaches intended to identify the learning rules being used by subjects in experiments with normal form games. This is done by simulating experimental data and then estimating the econometric models on the simulated data to determine if they can correctly identify the rule that was used to generate the data. The results show that all of the models examined possess difficulties in accurately distinguishing between the data generating processes.

In this paper I discuss economic processes that may give rise to spatial patterns in data, and explore the relative merits of alternative modeling approaches when data are spatially correlated. Specifically, I present an estimation scheme that allows for spatial random effects, and focus attention on cases in which such a framework may be preferred to the more general fixed effects framework that nests it. I use the models presented, together with information on the location of households in an Indonesian socio-economic survey, to test spatial relationships in Indonesian demand for rice.

This paper considers a generalized mean value m(p) defined implicitly for a probability measure p on the reals as the unique y for which J +(x, y) dp(x) = 0, where 0 is skewsymmetric and strictly increasing in its first argument. Conditions on m that are necessary and sufficient for the implicit characterization are given and its relationship to certainty equivalence is discussed.