Knowledge that Transforms

A labor-market model of search and transitions is analyzed where certain jobs carry layoff prospects and others do not. The dynamic value functions are solved for reservation wages for searchers with a choice between these jobs. For the laid-off worker, the wage at the prior job emerges as an important determinant of the optimal search strategy. Similarly, prospect of layoff is an important consideration for permanently separated workers during search. Conditioning on the nonparametric estimates of the reservation wages, the model is estimated using data from the Employment Opportunities Pilot Project survey.

In a recent paper, Yoram C. Peles and Meir I. Schneller (1989) ignore the sampling autocorrelation bias. A replication of their work that removes the bias changes their results. With the bias removed, there is no evidence that their three long-term ratios follow an adjustment process.

Donald H. Dutkowsky, William G. Foote, Intertemporal Substitution in Macroeconomics: Consumption, Labor Supply, and Money Demand, The Review of Economics and Statistics, Vol. 74, No. 2 (May, 1992), pp. 333-338

Susan Feigenbaum, Gerard Anderson, Judith R. Lave, Medicare's Prospective Payment System: The Victim of Aggregation Bias?, The Review of Economics and Statistics, Vol. 74, No. 1 (Feb., 1992), pp. 185-191

The information value of central bank announcements of projected future money growth is shown to depend both on the accuracy of the announcements and the extent to which the announcements themselves are anticipated by the public. The authors construct a new data set on internal Federal Reserve money projections. These projections, which are kept secret while they are in force, are comparable in many important respects to publicly announced Bank of Japan money projections. Using a derivative of the law of iterated projections, the authors estimate the information value of disclosure on the part of the Bank of Japan and the cost of secrecy on the part of the Federal Reserve. They find that the value of the information provided by the Bank of Japan has been small in terms of reducing money surprises, but that disclosure by the Federal Reserve would have significantly reduced money surprises in the United States.

This paper examines evidence about whether workers' compensation adjudicators "split the difference" between the parties' positions. It uses data from a workers' compensation system that provide information about the parties' final offers in both settled and adjudicated cases. Estimates of an "equitable settlement" offer fit the data quite well (R squared = 0.87). They are consistent with the hypothesis that only the parties' positions affected the adjudicator's decision and that the parties' position had equal weight. Adjudicator's did not rely less on more disparate positions. Still, other factors had a strong impact on the parties' positions, which in turn affected the final ratings.

Econometric analysis of duration data raises difficult issues of statistical inference. Building on the work of Prentice (1974) and Farewell and Prentice (1977), Addison and Portugal (1987; henceforth, AP) use the extended generalized gamma (EGG) distribution to test the sensitivity of regression estimates to more restrictive distributional assumptions which frequently have been imposed by other studies. AP find that these restrictions are rejected by data from the 1984 Displaced Worker Survey (DWS) and that imposing them creates large and variable biases in the estimated effects of the independent variables. AP also find that very different distributional forms provide the best fit for two subsamples of displaced workers. Both results suggest that many findings from earlier studies using simple parametric hazard models of unemployment duration are not robust. In this comment, we show that the sensitivity of AP's estimation results to distributional assumptions is a consequence of using an endogenous criteria to stratify the estimation sample, namely, whether or not workers collect Ul. This is an especially serious problem for a sample of displaced workers, because (a) many workers report jobless spells of zero or very few weeks; and (b) most displaced workers are Ul eligible. We also identify several other limitations of the DWS data for estimating unemployment durations and perform sensitivity analysis.

This paper develops a separable functional form in which all the relevant aggregator functions are modeled.to the desired degree of approximation. This leads to separable structures that are more flexible than those implied by parametric restrictions of flexible functional forms. Tests of separability can then be accomplished in a nonnested framework. This approach is illustrated with an application to input-output separability for a multiproduct translog cost function using a robust likelihood ratio testing procedure.

When the regression error variance is constant within subsets of data but differs across the subsets, grouped heteroskedasticity exists. Most tests for grouped heteroskedasticity are based on an asymptotic chi squared variable, and how well they perform in small samples is unknown. In this stud y, the performance of several of these, along with Breusch-Pagan tests, is examined using Monte Carlo methods. Generally, it is found that the tests that tend to be the easiest to apply and use the fewest assumptions are at least as good as somewhat more elaborate procedures.