R. W. Hafer

The sensitivity of VAR forecasts to alternative lag structures

Abstract Although numerous articles examine the effect on VAR forecasts from changes in the variables included in a model, little has been done to examine the effect that changing the lag structure has on forecasting accuracy. The latter analysis is made difficult by the fact that no overriding rule exists for ex ante selection of lag length in such models. This paper examines the sensitivity of forecasts from a VAR model using different lag structures. Holding constant the variables included and the time period studied, different lag structures are used. For example, we use simple ad hoc rules as well as statistical criteria, such as mean square error and Bayesian rules. Our results indicate that the accuracy of VAR forecasts varies dramatically across alternative lag structures. Moreover, our results show relatively short-lagged models to be more accurate, on average, than longer-lagged specifications.

Market and Survey Forecasts of the Three-Month Treasury-Bill Rate

In this article, four readily available one-quarter-ahead forecasts of the three-month U.S. Treasury bill rate are compared. The forecasts considered are (1) a prediction from the futures market, (2) a forecast derived from an implicit forward rate calculation, (3) a survey-gathered forecast, and (4) a no-change forecast. Each forecast is examined for general forecast accuracy and for the extent of bias contained in each forecast over the twelve-year period 1977-88. Results indicate that the futures rate statistically dominates the other three forecasts, while the survey and forward rate projections generally are found to be the least accurate and most biased. Copyright 1992 by University of Chicago Press.

The Economics of Non-Human Societies

In this book, Gordon Tullock offers a general theory of society, i.e., a theory encompassing both human and non-human societies. His strategy is to apply to non-human societies the tools that have evolved in economics. Specifically, Tullocks thesis says that the behavior of the social insects can be thought of as the interaction of preference functions and the environmental consequences of individual behavior. Thus, a theory evolves that, in principle, is capable of predicting whether a given species will survive in a particular niche. Mixed in with the theoretical discussion is an engaging description of several non-human species. Given Tullocks success in applying economic tools to political problems, it will be interesting to see if bioeconomics attains the stature of public choice. (JEL B49)

Inflation uncertainty and a test of the Friedman hypothesis

This paper tests Friedmans (1977) hypothesis that increases in inflation uncertainty, ceteris paribus, may yield higher levels of unemployment. Tests are made using quarterly measures of inflation uncertainty taken from the ASA-NBER survey. Using the 1972-1984 period, we find general support for the hypothesis.

Linkage in EMS term structures: evidence from common trend and transitory components

Abstract We test for the link among selected EMS term structures during 1979–1995. By decomposing each term structure into its common trend and transitory components, we find that EMS common trends move together over time, that the German trend is not the driving source of the shared co-movements, and that the transitory components (‘spread’) are more loosely linked in recent years perhaps due to widened exchange rate bands. Our findings refute arguments that Germany plays a dominant role in setting policy and raise doubts that it will play a dominant role if and when EMU takes place.

Entrepreneurship and state economic growth

Purpose - The purpose of this paper is to test whether entrepreneurship is a significant factor in explaining economic growth at the state level. Design/methodology/approach - This paper, unlike previous work, uses the Kauffman Index of Entrepreneurial Activity (KIEA) as the measure of entrepreneurial activity. Based on standard growth regressions using real per capita gross state product, real per capita personal income and employment growth, we test for the independent role that entrepreneurial activity may have on state economic growth. Findings - We find that an increase in the level of entrepreneurial activity is robustly associated with an increase in economic growth. Such findings reinforce calls for policy changes at the state level that promote more productive entrepreneurship. Research limitations/implications - These conclusions are tentative. The findings are based on the growth of the 50 states over a relatively short period. A longer data set would be preferable, if data were available. Moreover, the author has not attempted to distinguish between different categories of entrepreneurship, for example productive and unproductive entrepreneurship. Practical implications - Such findings reinforce calls for policy changes at the state level that promote more productive entrepreneurship. This would include, among others, changes such as reducing or eliminating state income taxes and setting strict limits on the governments use of eminent domain and environmental property takings. Originality/value - The study uses the Kauffman Index of Entrepreneurial Activity (KIEA), arguably a superior measure of state-level entrepreneurial activity, to explain state economic growth. The topic is timely and the results have important policy implications.

Well-Being and Economic Freedom: Evidence from the States

There is ample evidence that well-being, measured in various ways, is positively related to economic freedom across countries. Does this relationship hold at the sub-national level? Answering that question is the purpose of this study. Using regression analysis, we test whether economic freedom has an independent effect on well-being across states in the U.S. Our evidence indicates that, at the state-level, improvements in economic freedom lead to higher levels of well-being even after controlling for other economic factors. We also find that the relationship between well-being and economic freedom differs significantly across regions in the United States.

PREDICTING THE MONEY MULTIPLIER Forecasts from Component and Aggregate Models

Abstract This paper compares the relative abilities of two money multiplier forecasting procedures. The components method models and forecasts the multipliers individual ratios. The second procedure is simply to model and forecast the aggregate multiplier itself. It has been suggested, though untested, that the components approach is more accurate in forecasting, because it accounts for certain ratio-specific changes that are masked in the aggregate model. The evidence presented here, based on forecasts of the MI multiplier for the period January 1980 through December 1982, indicates that the aggregate model forecasts the multiplier as well as the component procedure.

Detrending and the Money-Output Link: International Evidence

An important policy question is whether nominal money is relatively more useful than interest rates in explaining movements in real output. Previous analyses usually rely only on U.S. data or other financially developed countries from a specific region, such as the EU. This study examines the empirical relation between money, interest rates, and output across a sample of 20 countries, including industrial countries from different regions as well as economically and financially less-developed countries. On the basis of estimating an unconstrained, four-variable VAR model, the weight of evidence indicates that rejecting money as a potentially informative tool in setting monetary policy is unwarranted.

The relationship between inflation and its variability: International evidence from the 1970s

Abstract This paper reexamines the empirical relationship between the average level of inflation and its variability. Based on a sample of 40 diverse economies, our results suggest that no one group of countries was able to avoid the decreased inflation predictability associated with higher levels of inflation during the 1970s. In contrast, previous research showed that Highly Industrialized countries, as a group, were able to control inflation variability during the period 1950–1970. Our results also suggest that the “threshold” level of inflation appears to have risen substantially during the 1970s. Whereas previous research suggested an upper bound of the threshold at about a four percent rate of inflation, the evidence from the 1970s indicates that the threshold may have risen to about a nine percent inflation rate.