Combining information for prediction in linear regression

This article deals with the prediction problem in linear regression where the measurements are obtained using k different devices or collected from k different independent sources. For the case of k=2, a Graybill-Deal type combined estimtor for the regression parameters is shown to dominate the individual least squares estimators under the covariance criterion. Two predictors ŷ _c and ŷ _p are proposed. ŷ _c is based on a combined estimator of the regression coefficient vector, and ŷ _p is obtained by combining the individual predictors from different models. Prediction mean square errors of both predictors are derived. It is shown that the predictor ŷ _p is better than the individual predictors for k≥2 and the predictor ŷ _c is better than the individual predictors for k=2. Numerical comparison between ŷ _c and ŷ _p shows that the former is superior to the latter for the case k=2.     

E-banking comes to town: Exploring how traditional UK high street banks are meeting the challenge of technology and virtual relationships

UK high street banks are continuing to extend the choice of channel through which customers can manage their moneycolon; an obvious example is e-banking. They have been keen to exploit technological advances and changing customer attitudes to alternative channels. Additionally, competition from leaner new market entrants has provided an added incentive to adopt new approaches. In the light of such developments, it is worth reflecting on the changing nature of the bank–customer relationship. This paper suggests that banks are finding it difficult to manage relationships effectively due, in large measure, to the sheer volume of customer data generated by new interactive, technology-based channels. Paradoxically, it seems that the more data banks have about customers the less likely they are to know them on a personal level. It is further suggested that channels such as e-banking potentially reduce the level of personal contact between bank and customer to the extent that a ‘virtual’ relationship develops. This paper concludes that, given the tendency towards ‘virtualisation’, it is inconceivable that bank–customer relationships will become any more intimate in the future. Indeed, a greater degree of personalisation in customer communication may be the very best that banks are able to offer.     

A Study of Arbitrage Efficiency Between the FTSE‐100 Index Futures and Options Contracts

Despite the importance of the London markets and the significance of the relationship for market makers, little published research is available on arbitrage between the FTSE‐100 Index futures and the FTSE‐100 European index options contracts. This study uses the put–call–futures parity condition to throw light on the relationship between options and futures written against the FTSE Index. The arbitrage methodology adopted in this study avoids many of the problems that have affected prior research on the relationship between options or futures prices and the underlying index. The problems that arise from nonsynchroneity between options and futures prices are reduced by the matching of options and futures prices within narrow time intervals with time‐stamped transaction data. This study allows for realistic trading and market‐impact costs. The feasibility of strategies such as execute‐and‐hold and early unwinding is examined with both ex‐post and ex‐ante simulation tests that take into consideration possible execution time lags for the arbitrage trade. This study reveals that the occurrence of matched put–call–futures trios exhibits a U‐shaped intraday pattern with a concentration at both open and close, although the magnitude of observed mispricings has no discernible intraday pattern. Ex‐post arbitrage profits for traders facing transaction costs are concentrated in at‐the‐money options. As in other major markets, despite important microstructure differences, opportunities are generally rapidly extinguished in less than 3 min. The results suggest that arbitrage opportunities for traders facing transaction costs are small in number and confirm the efficiency of trading on the London International Financial Futures and Options Exchange. © 2002 John Wiley & Sons, Inc. Jrl Fut Mark 22:31–58, 2002     

Does Hedging Affect Firm Value? Evidence from the US Airline Industry

Does hedging add value to the firm, and if so, is the source of the added value consistent with hedging theory? We investigate jet fuel hedging behavior of firms in the US airline industry during 1992–2003 to examine whether such hedging is a source of value for these companies. We illustrate that the investment and financing climate in the airline industry conforms well to the theoretical framework of Froot, Scharfstein, and Stein (1993). In general, airline industry investment opportunities correlate positively with jet fuel costs, while higher fuel costs are consistent with lower cash flow. Given that jet fuel costs are hedgeable, airlines with a desire for expansion may find value in hedging future purchases of jet fuel. Our results show that jet fuel hedging is positively related to airline firm value. The coefficients on the hedging variables in our regression analysis suggest that the “hedging premium” is greater than the 5% documented in Allayannis and Weston (2001), and might be as large as 10%. We find that the positive relation between hedging and value increases in capital investment, and that most of the hedging premium is attributable to the interaction of hedging with investment. This result is consistent with the assertion that the principal benefit of jet fuel hedging by airlines comes from reduction of underinvestment costs.     

Are Fundamentals Priced in the Bond Market?*

To date, the discussion of the Lev and Thiagarajan 1993 fundamentals in the prior literature has been exclusively in the context of the stock market. Our study is the first to examine the value‐relevance of these fundamentals for default risk. By focusing on the market for new bond issues, we examine the value‐relevance of the fundamental score using expected rather than realized returns. Also, by focusing on the bond market we provide a different perspective than that brought by prior studies relying solely on stock prices. We find the fundamentals to be priced in the market for new bond issues as indicators of expected future earnings and to be value‐relevant in enabling the market to discern differences in bond credit quality over and above the published bond ratings.     

Analysing Materials and Energy Flows in an Industrial District using an Enterprise Input–Output Model

Recent approaches to sustainable development leave much room for policies at a local level. In fact, it is becoming evident that targets such as increasing resource productivity, preserving natural cycles, or extending the present level of welfare, are best pursued within the confines of a local area. In particular, environmental changes are best brought about by considering local systems of firms as cornerstones of cooperative strategies and using data on materials and energy use in physical terms. In this paper, an enterprise input–output model is developed for an industrial district, i.e. a local group of firms specialized in the production of a single final output. The model allows for a detailed quantitative analysis of materials and energy flows and the consequent generation of waste and pollution. As a planning tool, the model may be used to evaluate alternative scenarios, such as the possibility of re- using waste taking account of sustainability requirements. An empirical case study applies the model to an industrial district in Southern Italy producing leather sofas.     

Consistent estimation in the bilinear multivariate errors-in-variables model

A bilinear multivariate errors-in-variables model is considered. It corresponds to an overdetermined set of linear equations AXB=C, A∈ℝ^m×n, B∈ℝ^p×q, in which the data A, B, C are perturbed by errors. The total least squares estimator is inconsistent in this case.  An adjusted least squares estimator is constructed, which converges to the true value X, as m →∞, q →∞. A small sample modification of the estimator is presented, which is more stable for small m and q and is asymptotically equivalent to the adjusted least squares estimator. The theoretical results are confirmed by a simulation study. Acknowledgements. We thank two anonymous reviewers for their suggestions and corrections.? A. Kukush is supported by a postdoctoral research fellowship of the Belgian office for Scientific, Technical and Cultural Affairs, promoting Scientific and Technical Collaboration with Central and Eastern Europe.? S. Van Huffel is a full professor with the Katholieke Universiteit Leuven.? I. Markovsky is a research assistant with the Katholieke Universiteit Leuven.? This paper presents research results of the Belgian Programme on Interuniversity Poles of Attraction (IUAP V-22), initiated by the Belgian State, Prime Minister's Office – Federal Office for Scientific, Technical and Cultural Affairs of the Concerted Research Action (GOA) projects of the Flemish Government MEFISTO-666 (Mathematical Engineering for Information and Communication Systems Technology), of the IDO/99/03 project (K.U. Leuven) “Predictive computer models for medical classification problems using patient data and expert knowledge”, of the FWO projects G.0078.01, G.0200.00, and G0.0270.02.? The scientific responsibility is assumed by its authors.