VAR,ERROR CORRECTION AND PRETEST FORECASTS AT LONG HORIZONS

This paper focuses on the construction of forecasts over long horizons where a typical long-horizon forecast might span four years using 20 to 40 years’ data. It is argued that the presence of persistence in the form of unit or near-unit autoregressive roots poses substantial difficulties for long-horizon interval and point forecasting. These difficulties may not be overcome even by efficient pre-testing or model-selection procedures and might, in general, lead to point forecasts with large asymptotic root mean squared errors and undesirably wide prediction intervals.     

Bond Yields, Ratings, and Financial Information: Evidence from Public Utility Issues

This study investigates the relative roles of bond ratings and financial information in the setting of bond yields. Structural equation modeling techniques are used to learn whether ratings determine yields or whether both ratings and yields are determined by a concurrent set of economic and financial factors. Tests of alternative structural model configurations provide evidence regarding the associations between bond ratings, financial information, and bond yields. Both ratings and financial information are found to play an important role in determining bond yields. In addition, yields are consistent with the higher rating in cases of split ratings.     

The local economic impact of construction projects in a small and relatively self-contained economy: The case of Lancaster University

Whilst the local multiplier impacts of the annual operation of universities has been the subject of intensive research, the economic impacts of capital construction projects have been almost completely ignored. This paper presents the results of detailed analysis of capital projects at Lancaster University in 1993-The reasons for the radically different annual operation and construction multipliers estimated in the Lancaster study are examined. Despite the smaller size of construction multipliers it is argued that it is a serious mistake to estimate local construction multipliers by making simplifying assumptions on the size of the key parameters in the multiplier equations.     

Two-Part Trade Policy under Imperfect Competition

In this paper we consider the potential gain of a government pursuing a two-part trade policy: an import license for entry, along with a per-unit tariff on imports. The model is a two-stage game of complete but imperfect information. In the first stage, the domestic government sets trade policy, while in the second stage the home and foreign producers behave as Cournot competitors. The paper demonstrates that the optimal trade policy depends upon the number of firms, the degree of heterogeneity in cost functions, and the degree of convexity in cost functions.     

THE LOCATION OF NONMETROPOLITAN HIGH-TECH INDUSTRIES: A Comparison of Regional Determinants

A study of the location of three classifications of high-tech industries in rural areas was undertaken using ordinary least squares, Tobit, and a two-step estimation procedure suggested by Heckman (1976). The results indicate that the location decision for high tech firms is influenced primarily by the county population, adjacency to an SMSA, and the expenditures on public infrastructure (exclusive of education expenditures). However, location near interstate highways was generally not a significant factor. Results were similar between branch and unit (single ownership) plants. Some differences in signs of orders of magnitude occurred among the estimation procedures. Making a choice between Tobit and Heckman approaches depends upon the goal of the research.