Generalized piecewise linear histograms

We extend the concept of piecewise linear histogram introduced recently by Beirlant, Berlinet and Györfi. The disadvantage of that histogram is that in many models it takes on negative values with probability close to 1. We show that for a wide set of models, the extended class of estimates contains a bona fide density with probability tending to 1 as the sample size n increases to infinity. The mean integrated absolute error in the extended class of estimators decreases with the same rate n^–2/5 as in the original narrower class.     

Ex ante assessment of the returns to livestock disease control in Indonesia

Agriculture's importance in the process of economic growth highlights the role of sustained advances in farm production practices by improving the quantity and quality of farm products. In this context, investment in improved agricultural technology continues to be an important avenue of assistance to the developing countries. However, the increased resource pressures facing both aid donors and recipients have emphasised the need for the prior assessment of the potential benefits of aid projects to assist effective aid planning and management. Here, the main requirements are to establish viable project goals for translation into effective programmes, to predict the likely project impacts, and to evaluate the potential benefits and costs of adopting the project's outcomes. An ex ante assessment of assistance in controlling a major livestock disease in Indonesia's eastern islands is described in this paper. The annual net benefits from controlling this disease ranged between $A0.45 and $A2.5 million according to the mortality rate reduction achieved. The benefits were shared between beef producers and consumers according to the market elasticity conditions assumed.     

Evidence on the motivation for management forecasts of corporate earnings

A multivariate model of the process by which managers decide to release public forecasts of their firms' earnings is developed, based on factors that are hypothesized to affect the demand for and the willingness to supply such forecasts. We test the model on data from a comprehensive sample of earnings forecasts, and find support for our hypotheses about the likely joint influence of those factors. Larger firm size, greater leverage, higher and more stable earnings rates and less rapid growth rates are found to be associated with an increased propensity for management to provide earnings forecasts for their firms.     

Job Security Provisions and Employment: Revised Estimates

This article provides estimates of the effect of statutory severance pay and notice on four labor market outcome indicators, closely following Lazear (1990) but correcting for errors in his dependent variables and covariates. Although we corroborate the directional influence of severance pay for three of the indicators, there is little to suggest that its contribution to rising unemployment is material. Also contrary to Lazear, longer notice appears to be associated with broadly favorable outcomes.     

The Mode of Acquisition in Takeovers: Taxes and Asymmetric Information

We develop a model in which the mode of acquisition conveys information concerning the value of the bidder. The model incorporates the possibility that offers containing both cash and stock can be made in a setting consistent with the U.S. tax code. We demonstrate that bidders with unfavorable private information about their equity value choose offers containing some stock to avoid the capital gains tax consequences of cash offers. The model yields a number of unique predictions about the construction of acquisition offers. We present evidence consistent with the model.     

Looking for contagion in currency futures markets

This article tests whether there are pure contagion effects in both conditional means and volatilities among British pound, Canadian dollar, Deutsche mark, and Swiss franc futures markets during the 1992 ERM crisis. A conditional version of international capital asset pricing model (ICAPM) in the absence of purchasing power parity (PPP) is used to control for economic fundamentals. The empirical results indicate that overall there are no mean spillovers among those futures markets, but they are detected during the crisis period. That is, past return shocks originating in any one of the four markets have no impact on the other three markets during the entire sample period, suggesting that these markets are weak‐form efficient. However, this weak‐form market efficiency fails to hold during the market turmoil, especially for British pound and Swiss franc, and the sources of contagion‐in‐mean effects are mainly due to the return shocks originating in three European currency futures markets. As for the contagion‐in‐volatility, it is detected for British pound only because its conditional volatility is influenced by the negative volatility shocks from Canadian dollar, Deutsche mark, and Swiss franc, with Deutsche mark playing the dominant role in generating these shocks. JEL Classifications: C32; F31; G12. © 2003 Wiley Periodicals, Inc. Jrl Fut Mark 23:957–988, 2003     

MANAGING VENDOR INVENTORY IN A DUAL LEVEL DISTRIBUTION SYSTEM

Collaborative arrangements among members of the supply chain have received a great deal of interest in recent years as a means of reducing costs. One such arrangement is vendor managed inventory (VMI). VMI allows the vendor to make decisions concerning the quantity and timing of deliveries to the retailer. Such an arrangement offers the potential of a more efficient supply chain by removing the negative effects of retail ordering policies. A thorough review of the literature was conducted to identify factors likely to impact the performance of a VMI partnership. Computer simulation was used to study the effects of these factors from both the vendor's and retailer's perspectives. The results lend insight into the performance of VMI and guidance for managers as to the environments in which VMI is most effective.     

THE EFFECT OF INVESTMENT IN INTERORGANIZATIONAL INFORMATION TECHNOLOGY IN A RETAIL SUPPLY CHAIN

The primary purpose of this research was to investigate the effect of investment in information technology in a supply chain. The results of that investigation are presented by focusing on an empirically tested supply chain relationship model containing both behavioral and operational constructs. The four behavioral constructs represented in the model are relationship trust, relationship commitment, relationship dependence, and long‐term relationship orientation. The four operational constructs represented in the model are retailer investment in interorganizational information technology, perceived supplier investment in interorganizational information technology, logistics efficiency, and logistics effectiveness. Among other findings, the results of the investigation found that perceived supplier investment in interorganizational information technology has a significant and positive effect on logistics efficiency.     

RELATIONSHIP MAGNITUDE AND ITS ROLE IN INTERORGANIZATIONAL RELATIONSHIP STRUCTURE

Close relationships between and among supply chain members are becoming more prevalent. However, there is lack of agreement in the literature and in practice concerning the characteristics of different interorganizational relationships. The resultant confusion is an obstacle to the progression of research and could cause problems among firms in a supply chain. Based on previous research and an exploratory study conducted with company executives responsible for supply chain management activities, this article seeks to introduce the concept of relationship magnitude (i.e., the extent or degree of closeness or strength of the relationship) and differentiate it from relationship type (i.e., classes of relationships that share common traits). Implications for managers and opportunities for future research are provided.     

Conditioning as disintegration

Conditional probability distributions seem to have a bad reputation when it comes to rigorous treatment of conditioning. Technical arguments are published as manipulations of Radon–Nikodym derivatives, although we all secretly perform heuristic calculations using elementary definitions of conditional probabilities. In print, measurability and averaging properties substitute for intuitive ideas about random variables behaving like constants given particular conditioning information.
One way to engage in rigorous, guilt-free manipulation of conditional distributions is to treat them as disintegrating measures—families of probability measures concentrating on the level sets of a conditioning statistic. In this paper we present a little theory and a range of examples—from EM algorithms and the Neyman factorization, through Bayes theory and marginalization paradoxes—to suggest that disintegrations have both intuitive appeal and the rigor needed for many problems in mathematical statistics.