Research Database

This paper is a case study of the use of vector autoregression (VAR) models to test economic theories. It focuses on the work of Christopher A. Sims, who in 1980 found that relationships in economic data generated by a small VAR model were inconsistent with those implied by a simple form of monetarist theory. The paper describes the work of researchers who criticized Sims' results as not robust and Sims' response to these critics. The paper reexamines all of this work by estimating hundreds of variations of Sims' model. The paper concludes that both Sims and his critics are right: Sims' conclusion about monetarism is robust, but some of his other statistical results are not. In general, the paper concludes that VAR models can be used to test theories, but that any relationships they uncover in the data must be carefully checked for robustness.

We propose and evaluate an explicit test of the null hypothesis of no difference in the accuracy of two competing forecasts. In contrast to previously developed tests, a wide variety of accuracy measures can be used (in particular, the loss function need not be quadratic, and need not even be symmetric), and forecast errors can be non-Gaussian, nonzero mean, serially correlated and contemporaneously correlated.

A real business cycle model with heterogeneous agents is parameterized, calibrated, and simulated to see if it can account for some stylized facts characterizing postwar U.S. business cycle fluctuations, such as the countercyclical movement of labor’s share of income, and the acyclical behavior of real wages. There are two types of agents in the model, workers and entrepreneurs, who participate on an economy-wide market for contingent claims. On this market workers purchase insurance from entrepreneurs, through optimal labor contracts, against losses in income due to business cycle fluctuations. The model is used to study the allocation of risk and the distribution of income over the business cycle.

Why did states agree to a U.S. Constitution that prohibits them from issuing their own money? This article argues that two common answers to this question—a fear of inflation and a desire to control what money qualifies as legal tender—do not fit the facts. The article proposes a better answer: a desire to form a viable monetary union that both eliminates the variability of exchange rates between various forms of money and avoids the seigniorage problem that otherwise occurs in a fixed exchange rate system. Supporting evidence is offered from three periods of U.S. history: the colonial period (1690–1776), the Revolutionary War (1776–83), and the Confederation period (1783–89).

Estimates of interindustry wage differentials are obtained using a fixed-effects estimator on a long panel, the National Longitudinal Survey of Young Men (NLS). After controlling for observable worker characteristics, 84 percent of the residual variance of log wages across industries is explained by individual fixed-effects. Only 16 percent of the residual variance is “explained” by industry dummies. Since no controls for specific job characteristics are used, job characteristics that vary across industries could potentially explain this rather small residual across-industry log wage variance that is not attributable to individual effects. Clearly then, these data do not force us to resort to noncompetitive explanations of interindustry wage differentials, such as efficiency wage theory. Furthermore, efficiency wage theories predict that wages in efficiency wage paying (or primary) industries should be relatively rigid. Therefore, industry wage differentials should widen in recessions. However, no such tendency is found in the data.

This study overturns the conclusion of a 1990 study by David Humphrey and Allen Berger, which found that check float is responsible for the popularity of checks despite their high resource cost compared to electronic payment instruments. The new study examines recent data on the costs of checks and automated clearinghouse (ACH) payments. It finds that the value of check float has decreased significantly since the 1990 study and is no longer large enough to make checks more attractive than ACH payments. The study also questions whether the idea that float could be responsible for the persistent use of checks is reasonable given standard assumptions about the behavior of economic agents. The study ends by speculating on why checks are used more than less-costly alternatives and by encouraging policymakers to wait for researchers to adequately answer that question before intervening in the market for payment instruments.

This paper provides an algorithm for computing Markov Perfect Nash Equilibria (Maskin and Tirole, 1988a and b) for dynamic models that allow for heterogeneity among firms and idiosyncratic (or firm specific) sources of uncertainty. It has two purposes. To illustrate the ability of such models to reproduce important aspects of reality, and to provide a tool which, given appropriate parameter estimates, can be used for both descriptive and policy analysis in a setting which allows firms to differ from one another in ways that are consistent with the information in firm level data sets.

We illustrate by computing the policy functions, and simulating the industry structures, generated by a class of dynamic differentiated product models in which the idiosyncratic uncertainty is due to both the random outcomes of each firm's research process, and to an autonomous aggregate demand process. The illustration focuses on comparing the effect of different regulatory and behavioral assumptions on market structure and on welfare for one particular set of parameter values. The results here are of some independent interest and can be read without delving into the technical detail of the computational algorithm.

The last part of the paper begins with an explicit consideration of the computational burden of the algorithm, and then introduces approximation techniques designed to make computation easier. The purpose of this section is to enable us to compute equilibria for industries in which a large number of firms are typically active. Its major result is analytic. We show that if the value function of a given firm is exchangeable in the state vectors of its competitors, then the number of polynomial coefficients one needs for a given order of a polynomial approximation to that function is both independent of the number of firms active in the market, and a relatively small number. This enables us to use the approximation technique to reduce the computational burden of the algorithm dramatically.

We study the aggregate implications of (S,s) inventory policies in a dynamic general equilibrium model. Firms in the model's retail sector face idiosyncratic demand risk, and (S,s) inventory policies are optimal because of fixed order costs. The model economy replicates salient features of the business cycle and reconciles evidence that orders are more volatile than sales, and that inventory investment is positively correlated with sales. There are two main results. First, we find that general equilibrium effects and the optimal order size are important for the economy's response to exogenous shocks. Second, we find that key features of our results are independent of the presence of idiosyncratic risk.