Comparing Possibly Misspecified Forecasts

Abstract

Recent work has emphasized the importance of evaluating estimates of a statistical functional (such as a conditional mean, quantile, or distribution) using a loss function that is consistent for the functional of interest, of which there is an infinite number. If forecasters all use correctly specified models free from estimation error, and if the information sets of competing forecasters are nested, then the ranking induced by a single consistent loss function is sufficient for the ranking by any consistent loss function. This article shows, via analytical results and realistic simulation-based analyses, that the presence of misspecified models, parameter estimation error, or nonnested information sets, leads generally to sensitivity to the choice of (consistent) loss function. Thus, rather than merely specifying the target functional, which narrows the set of relevant loss functions only to the class of loss functions consistent for that functional, forecast consumers or survey designers should specify the single specific loss function that will be used to evaluate forecasts. An application to survey forecasts of U.S. inflation illustrates the results.     

How to Perform an Ethical Risk Analysis (eRA)

Ethical analysis is often needed in the preparation of policy decisions on risk. A three‐step method is proposed for performing an ethical risk analysis (eRA). In the first step, the people concerned are identified and categorized in terms of the distinct but compatible roles of being risk‐exposed, a beneficiary, or a decisionmaker. In the second step, a more detailed classification of roles and role combinations is performed, and ethically problematic role combinations are identified. In the third step, further ethical deliberation takes place, with an emphasis on individual risk‐benefit weighing, distributional analysis, rights analysis, and power analysis. Ethical issues pertaining to subsidiary risk roles, such as those of experts and journalists, are also treated in this phase. An eRA should supplement, not replace, a traditional risk analysis that puts emphasis on the probabilities and severities of undesirable events but does not cover ethical issues such as agency, interpersonal relationships, and justice.     

Interorganizational Determinants of Environmental Purchasing: Initial Evidence from the Consumer Products Industries*

Environmental purchasing consists of the purchasing function's involvement in activities that include reduction, recycling, reuse, and substitution of materials. Despite the potentially important role that the purchasing function can play in a firm's environmental activities, little research has been performed to date that examines the factors that impact environmental purchasing. The authors develop and empirically test a theoretical model that examines how interorganizational factors both drive and constrain purchasing's involvement in environmental activities. The empirical findings suggest that environmental purchasing activities will be facilitated through increased coordination with suppliers as well as downstream members of the supply chain, including retailers. The results also suggest the need for increased coordination within the firm, particularly between the purchasing function on the inbound side and marketing and distribution functions on the outbound side.     

Reconfiguring the Supply Network Using Current Performance Data

Reconfiguration of the supply chain network from time to time is essential for businesses to retain their competitive edge. This paper presents a methodology for reconfiguration of an existing supply chain network. The methodology is characterized by two decision levels. In the first level, the current network performance is evaluated and efficient practices are identified. In the next level, a model that incorporates efficient practices is developed to reconfigure the network. This integrated methodology allows for decision maker (DM) input throughout the process. The methodology has been implemented and tested in the reconfiguration of an outbound petroleum supply chain network for CountryMark Cooperative, Inc. In this case study, Data Envelopment Analysis (DEA) is used to analyze current operations and an integer programming (IP) model that incorporates efficiency metrics is developed for selection of distribution facilities and allocation of resources to the facilities. Use of this methodology can lead to improved operations and reduced operating expenses.     

Optimal Policy for a Reseller When the Supplier Offers a Temporary Reduction in Price*

A common practice in product distribution is the case in which the supplier offers a temporary reduction in price. It is suggested in the literature that in such situations, the reseller may engage in forward buying (i.e., purchasing additional stock at the reduced price offered by the supplier for later sale at the regular selling price). In this paper, a model is formulated of the reseller's response when the supplier offers a temporary reduction in price. It is assumed that the market demand for the product is elastic with respect to the selling price the reseller sets. A procedure for determining the optimal response of the reseller is developed. The model presented in this paper can easily be adapted to the case in which the reseller faces a permanent increase in the price charged by the supplier.     

Some robustness issues for comparing multiple logistic regression slopes to a control for small samples

For comparing several logistic regression slopes to that of a control for small sample sizes, Dasgupta et al. (2001) proposed an "asymptotic" small-sample test and a "pivoted" version of that test statistic. Their results show both methods perform well in terms of Type I error control and marginal power when the response is related to the explanatory variable via a logistic regression model. This study finds, via Monte Carlo simulations, that when the underlying relationship is probit, complementary log-log, linear, or even non-monotonic, the "asymptotic" and the "pivoted" small-sample methods perform fairly well in terms of Type I error control and marginal power. Unlike their large sample competitors, they are generally robust to departures from the logistic regression model.     

Coverage probabilities of nonparametric simultaneous confidence bands for a survival function

Simultaneous confidence bands provide a useful adjunct to the popular Kaplan–Meier product limit estimator for a survival function, particularly when results are displayed graphically. They allow an assessment of the magnitude of sampling errors and provide a graphical view of a formal goodness-of-fit test. In this paper we evaluate a modified version of Nair's (1981) simultaneous confidence bands. The modification is based on a logistic transformation of the Kaplan–Meier estimator. We show that the modified bands have some important practical advantages.     

邓小平收入分配理论在微观企业的实现机制

邓小平收入分配理论涉及收入分配要素、收入分配原则、收入分配目标及实现路径等问题。邓小平收入分配理论是我们收入分配实践的重要理论依据。企业是国民经济的基本单位。通过对邓小平收入分配理论的简单介绍,从三个方面分析了邓小平收入分配理论在微观企业的实现机制,以期对企业的收入分配机制设计有所裨益。     

Vertical cost information sharing in a supply chain with value-adding retailers

We consider a supply chain consisting of one supplier and two value-adding heterogeneous retailers. Each retailer has full knowledge about his own value-added cost structure that is unknown to the supplier and the other retailer. Assuming there is no horizontal information sharing between two retailers, we model the supply chain with a three-stage game-theoretic framework. In the first stage each retailer decides if he is willing to vertically disclose his private cost information to the supplier. In the second stage, given the information he has about the retailers, the supplier announces the wholesale price to the retailers. In response to the wholesale price, in the third stage, the retailers optimize their own retail prices and the values added to the product, respectively. Under certain conditions, we prove the existence of equilibrium prices and added values. Furthermore, we obtain the condition under which both retailers are unwilling to vertically share their private information with the supplier, as well as the conditions under which both retailers have incentives to reveal their cost information to the supplier, thus leading to a win–win situation for the whole supply chain.