Knowledge that Transforms

In the existing literature, conditional forecasts in the vector autoregressive (VAR) framework have not been commonly presented with probability distributions. This paper develops Bayesian methods for computing the exact finite-sample distribution of conditional forecasts. It broadens the class of conditional forecasts to which the methods can be applied. The methods work for both structural and reduced-form VAR models and, in contrast to common practices, account for parameter uncertainty in finite samples. Empirical examples under both a flat prior and a reference prior are provided to show the use of these methods.

Acommon model for security price dynamics is the continuous-time stochastic volatility model. For this model, Hull and White (1987) show that the price of a derivative claim is the conditional expectation of the Black-Scholes price with the forward integrated variance replacing the Black-Scholes variance. Implementing the Hull and White characterization requires both estimates of the price dynamics and the conditional distribution of the forward integrated variance given observed variables. Using daily data on close-to-close price movement and the daily range, we find that standard models do not fit the data very well and that a more general three-factor model does better, as it mimics the long-memory feature of financial volatility. We develop techniques for estimating the conditional distribution of the forward integrated variance given observed variables.

In this study, we use data for 1981 through 1994 on a large sample of U.S. companies to examine the persistence of incremental industry, corporate-parent, and business-specific effects on profitability. Our results indicate that the incremental effects of industry on profitability persist longer than the incremental effects of the corporate parent and of the specific business. Changes in industry structure have a more persistent impact on profitability than do changes in firm structure.

Research on the distribution of income during the 1980s has identified a trend towards increasing inequality, which may be the continuation and acceleration of trends spanning several decades. This paper explores to what extent behavioral responses to the tax changes during the 1980s may also explain the rising inequality. The 1986 Tax Reform Act is used as a natural experiment to explore the roles played by both taxes and a variety of nontax factors. Our principal finding is that both tax rates and nontax factors appear to have had significant effects on relative income growth during the late 1980s.

Theory suggests that vertical disintegration should be greater in areas where industries localize. This paper provides some evidence that this implication is true for the U.S. manufacturing sector. Purchased inputs as a percent of the value of output is used as a measure of vertical disintegration. To measure the localization of industry, for each manufacturing plant the amount of employment in neighboring plants in the same industry is determined.

We examine the effect of buyer merger on bilateral negotiations between a supplier and n buyers. Merger may have bargaining effects in addition to the usual efficiency effects. The effect of merger on the buyers' bargaining position depends on the curvature of the supplier's gross surplus function: merger enhances (worsens) the buyers' bargaining position if the function is concave (convex). Based on a panel of advertising revenue in the cable television industry, our estimates indicate that the gross surplus function for suppliers of program services is convex. This result suggests that cable operators integrate horizontally to realize efficiency gains rather than to enhance their bargaining position vis-a-vis program suppliers.

We provide a framework for evaluating and improving multivariate density forecasts. Among other things, the multivariate framework lets us evaluate the adequacy of density forecasts involving cross-variable interactions, such as time-varying conditional correlations. We also provide conditions under which a technique of density forecast “calibration” can be used to improve deficient density forecasts, and we show how the calibration method can be used to generate good density forecasts from econometric models, even when the conditional density is unknown. Finally, motivated by recent advances in financial risk management, we provide a detailed application to multivariate high-frequency exchange rate density forecasts.

A “grid” bootstrap method is proposed for confidence-interval construction, which has improved performance over conventional bootstrap methods when the sampling distribution depends upon the parameter of interest. The basic idea is to calculate the bootstrap distribution over a grid of values of the parameter of interest and form the confidence interval by the no-rejection principle. Our primary motivation is given by autoregressive models, where it is known that conventional bootstrap methods fail to provide correct first-order asymptotic coverage when an autoregressive root is close to unity. In contrast, the grid bootstrap is first-order correct globally in the parameter space. Simulation results verify these insights, suggesting that the grid bootstrap provides an important improvement over conventional methods. Gauss code that calculates the grid bootstrap intervals-and replicates the empirical work reported in this paper'is available from the author's Web page at www.ssc.wisc.edu˜bhansen

This paper examines the relationship between consumption smoothing and excess female mortality, by asking if favorable rainfall shocks in childhood increase the survival probabilities of girls to a greater extent than they increase boys' survival probabilities for a sample of rural Indian children. In order to avert the issue of selection bias due to underreporting of births of girls, a methodology is employed that does not require data on births by gender. The results indicate that favorable rainfall shocks increase the ratio of the probability that a girl survives to the probability that a boy survives.

This paper analyzes the link between rising city crime rates and urban flight. Each additional reported crime is associated with a roughly one-person decline in city population. Almost all of the crime-related population decline is attributable to increased out-migration rather than a decrease in new arrivals. Households that leave the city because of crime are much more likely to remain within the Standard Metropolitan Statistical Area (SMSA) than those that leave the city for other reasons. Migration decisions of highly educated households and those with children are particularly responsive to changes in crime. Causality appears to run from rising crime rates to city depopulation.