Knowledge that Transforms

This paper traces the time series (Growth of Firms) tradition in the study of market structure, and looks at how recent studies on entry and the size distribution of firms have modified thinking in this area.

The event study is an important research tool in economics and finance. The goal of an event study is to measure the effects of an economic event on the value of firms. Event study methods exploit the fact that, given rationality in the marketplace, the effects of an event will be reflected immediately in security prices. Thus the impact can be measured by examining security prices surrounding the event. In this paper event study methods are described including some of the potential complications. An example is included to illustrate the approach.

We develop a method for measuring the foresight agents have. We first dichotomize an agent’s information at current date t into knowledge up to date t 1 f and expectations after t 1 f. We then form a residual-based test statistic that allows us to compare prediction errors for econometric models based on different values of f. We illustrate the method, examining investment around tax reforms to measure the foresight firms have about tax policy. In this illustration, current investment appears to reflect currently available information but little foresight other than foresight of enacted policy changes.

We adapt techniques from the literature on chaos and nonlinear dynamics to detect misspecification in models of serially independent data by checking for dependence between the regressors and disturbances. Our tests are nonparametric in that they determine whether the distribution of the disturbances depends on the regressors without identifying a model of dependence or the distribution of the disturbances. In Monte Carlo simulations we find that these tests have good power against dependence caused by omitted variables, incorrect functional form, heteroskedasticity, and similar problems.We also apply our tests to detect misspecification in models of income imputation.

In GMM estimations, when data exhibit exponential trends, scaling factors are often used to restore stationarity in Euler equation residuals. The present paper demonstrates that finite-sample estimates are sensitive to the scaling factors, and seemingly plausible scaling factors may produce spurious estimates. It suggests that scaling factors be chosen so that the scaled marginal utility is roughly constant. The discussion is conducted through estimation of a representative agent's time-nonseparable utility function, using first artificial data and then aggregate consumption and asset returns.

Standard autocorrelation corrections applied to cointegrating regressions can lead to erroneous first-differencing. Such outcomes are shown to be possible under a range of environments, including cases with autocorrelation coefficients substantially less than 1. First-differencing of a cointegrating regression results in estimates that may bear little relation to the parameters in the original untransformed relation, resulting in misinterpretation of the parameter estimates. These results are proved analytically and demonstrated with simulations and empirical examples.

This note examines the asymptotic properties of the Wald statistic in vector autoregressions (VAR) that may have unit roots. Within this framework we extend the theoretical results to nonlinear restrictions. As an example we study constraints derived from linear(ized) rational expectations models focusing on the expectations hypothesis using U.S. term structure data. For such cross-equation restrictions the statistic has a nonstandard distribution because the restrictions constrain the row space of the total impact matrix of the VAR. A Monte Carlo study is performed, and we find that the test statistic is somewhat oversized in small samples.

Different versions of the score test for neglected heterogeneity for a right censored exponential model are analyzed. These tests depend on how the information matrix is estimated. A test based on the theoretical information matrix is derived that is shown to outperform all the other tests. Further, the noncentrality parameter of the test is examined to show how the power of the test is reduced when data are censored.

Hospitals expend considerable resources each year to provide health care to the poor. Why do some hospitals voluntarily take on a disproportionate burden of this care? Our view is that the burdened hospitals are not simply altruistic. They are indirectly compensated for this expense with legal protections against competition under certificate-ofneed (CON) regulation. We test this hypothesis in a recursive model, explaining which hospitals are likely to win CON approval. The results indicate that, controlling for the endogeneity of indigent care, regulators in Florida systematically awarded licenses to hospitals providing greater amounts of care to the poor. © 1997 by the President and Fellows of Harvard College and the Massachusetts Institute of Technology