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.     

North-South interdependence: An economic-physical interpretation

Summary The article gives a physical-economic interpretation to a number of economic North-South interdependent relations. Basic research evidence at the man-machine level was an inspiration; the output could only be expressed in physical specification terms. The corresponding generalizations are in product complexity, speciality terms also. This terminology is conducive to far-ranging extrapolations and generalizations. It eliminates the problem of pricing at the product level for all aggregation levels; therefore the fundamental economic relations are better expressed. The article concludes with a mega extrapolation in graphical terms, which relates the product and implied technological capability in the world, expressed in physical terms, for country groups ordered by three development levels. Correspondingly the comparative advantage and inter-industry trade areas at the world product level are shown.The author acknowledges valid comments of two anonymous referees and financial support by DGIS to the Technology Scientific Foundation for the research of which this paper reports certain aspects only. This paper came out as a working paper TSF 84-1. An earlier version was presented at the International Economic Association Meeting in Madrid, Sept. 1983. Clearly, only the author bears responsibility for the ideas and interpretations presented in the following text.     

The impact of time duration between trades on the price of treasury note futures contracts

Recent research in finance has indicated that the institutional structure in which financial asset prices are determined can have a nontrivial impact on pricing. This report examines transaction level data for Treasury Note futures contracts traded at the Chicago Board of Trade (CBOT) to identify institutional, or market microstructure, impacts on the pricing of these contracts. Relatively few articles have conducted empirical research on the microstructure of U.S. futures trading due to the limited availability of comprehensive transaction level data from the futures exchanges. This report uses the CBOT's Computerized Trade Reconstruction database, a comprehensive transaction level dataset, to identify the price impact of the time duration between trades in a manner analogous to that of A. Dufour and R. F. Engle (2000). Unique differences from prior research include the application to futures contracts with their relative higher frequency of trading, as well as the investigation of the price impact of the number of active traders present on the trading floor and the trading volume. Subsequent price and sign of trade significantly relate to the time duration between trades, the number of floor brokers, and the trading volume. © 2004 Wiley Periodicals, Inc. Jrl. Fut Mark 24:965–980, 2004     

The contribution of a satellite market to price discovery: Evidence from the Singapore exchange

The Singapore Exchange (SGX), a small satellite market, successfully competes with a large home market, the Osaka Securities Exchange (OSE), in trading the Nikkei 225 futures index. In this paper, we investigate the contribution of the SGX to price discovery and shed light on the reasons for its continued success. Evidence is provided from information revelation and price discovery of three competing but informationally linked markets of the Nikkei 225 index—domestic spot (Tokyo Stock Exchange), domestic futures (OSE), and foreign futures (SGX), which represents the satellite market. Overall, the futures market contributes 77% to price discovery, with the satellite market contributing 42% of the futures and 33% of the total price discovery. These figures, surprisingly, far exceed the satellite market's share of trading volume. Support is provided for the extended trading hours on the SGX for three of the four non‐overlapping trading sub‐periods. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:981–1004, 2004     

Contract modifications and the basis behavior of live cattle futures

The purpose of this study was to assess the basis behavior of the Live Cattle Futures contract at the Chicago Mercantile Exchange (CME) before and after the 1995 contract changes. Additionally, an alternative method of basis calculation utilizing weighted mean futures prices versus settlement futures prices was compared to determine which method provides a better representation of the basis level. Within a regression model with heteroskedascity error framework, we found that the level of nearby basis in the period after June 1995 has shifted lower and the average monthly open interest of net commercial long positions has substantially increased after the contract modifications. These empirical results are consistent with the notion that more long activity entered the market in response to the contract modifications. Additionally, an alternative (new) measure of basis calculation (cash price minus weighted mean futures price) produced similar results to two other commonly used measures. In conclusion, the 1995 contract changes have neither increased nor decreased the volatility of live cattle basis. © 2004 Wiley Periodicals, Inc. Jrl Fut Mark 24:557–590, 2004     

CROSS‐DOCKING AND ITS IMPLICATIONS IN LOCATION‐DISTRIBUTION SYSTEMS

Cross‐docking replaces traditional warehousing, enabling continuous flow of items without storage. Here we model location‐distribution networks, that include cross‐docking facilities, to obtain the latter's impact on the supply chain. We formulate optimization models to minimize total cost in three multi‐echelon networks, each model generalizing the preceding one. The first includes a single manufacturer, one product type, and multiple customers. Cross‐docks are to be located between origin and destinations. Besides solving optimally, a tool for quantitative analysis of direct‐shipment decisions is developed. The second model considers more than one product: We determine a cost‐effective sequence of items for indirect shipment (via cross‐docks). Finally, in a network with multiple origins, optimal solutions are obtained for 40 medium‐sized and larger examples.