供应链风险评估:一个贝叶斯——量子决策的推理网络研究范式

为了分析供应链运作过程中存在风险的性质,采用贝叶斯网的方式,构建了供应链风险因素、风险事件之间的系统模型,并在量子概率的基础上,分析各种风险发生的规律,并分析了供应链风险事件之间存在的共同发生的可能性。结论认为:供应链风险是一个具有多源、多维、交叉等多种属性的复杂系统,其中,道德风险与牛鞭效应最容易发生,双重边际效应、资金链断裂以及牛鞭效应的影响最大;若干种风险之间按照一个较高的概率发生着共振现象。     

Meta-Functional Benefit Transfer for Wetland Valuation: Making the Most of Small Samples

This study applies functional Benefit Transfer via Meta-Regression Modeling to derive valuation estimates for wetlands in an actual policy setting of proposed groundwater transfers in Eastern Nevada. We illustrate how Bayesian estimation techniques can be used to overcome small sample problems notoriously present in Meta-functional Benefit Transfer. The highlights of our methodology are: (i) The hierarchical modeling of heteroskedasticity; (ii) The ability to incorporate additional information via refined priors; and (ii) The derivation of measures of model performance with the corresponding option of model-averaged Benefit Transfer predictions. Our results indicate that economic losses associated with the disappearance of these wetlands can be substantial and that primary valuation studies are warranted.      

Probabilistic Models for Bacterial Taxonomy

We give a survey of different partitioning methods that have been applied to bacterial taxonomy. We introduce a theoretical framework, which makes it possible to treat the various models in a unified way. The key concepts of our approach are prediction and storing of microbiological information in a Bayesian forecasting setting. We show that there is a close connection between classification and probabilistic identification and that, in fact, our approach ties these two concepts together in a coherent way.     

On large games with bounded essential coalition sizes

We consider games in characteristic function form where the worth of a group of players depends on the numbers of players of each of a finite number of types in the group. The games have bounded essential coalition sizes: all gains to cooperation can be achieved by coalitions bounded in absolute size (although larger coalitions are permitted they cannot realize larger per-capita gains). We show that the utility function of the corresponding "limit" market, introduced in Wooders (1988, 1994a) , is piecewise linear. The piecewise linearity is used to show that for almost all limiting ratios of percentages of player-types, as the games increase in size (numbers of players), asymptotically the games have cores containing only one payoff, and this payoff is symmetric (treats players of the same type identically). We use this result to show that for almost all limiting ratios of percentages of player-types, Shapley values of sequences of growing games converge to the unique limiting payoff.     

Bayesian and Frequentist Inference for Ecological Inference: The R×C Case

In this paper we propose Bayesian and frequentist approaches to ecological inference, based on R × C contingency tables, including a covariate. The proposed Bayesian model extends the binomial-beta hierarchical model developed by K ing , R osen and T anner (1999) from the 2×2 case to the R × C case. As in the 2×2 case, the inferential procedure employs Markov chain Monte Carlo (MCMC) methods. As such, the resulting MCMC analysis is rich but computationally intensive. The frequentist approach, based on first moments rather than on the entire likelihood, provides quick inference via nonlinear least-squares, while retaining good frequentist properties. The two approaches are illustrated with simulated data, as well as with real data on voting patterns in Weimar Germany. In the final section of the paper we provide an overview of a range of alternative inferential approaches which trade-off computational intensity for statistical efficiency.     

A Generalized Cameron–Martin Formula with Applications to Partially Observed Dynamic Portfolio Optimization

The optimal dynamic allocation problem for a Bayesian investor is addressed when the stock's drift—modeled as a linear mean-reverting diffusion—is not observed directly but only via the measurement process. Adopting a martingale approach, an appropriate generalization of the Cameron–Martin (1945) formula then enables computation of both the optimal dynamic allocation and the value function for a general utility function, in terms of an inverse Laplace transform of an explicit expression. Moreover, closed-form formulas are provided in the case of power utility.     

Modeling Clustered Ordered Categorical Data: A Survey

This article surveys various strategies for modeling ordered categorical (ordinal) response variables when the data have some type of clustering, extending a similar survey for binary data by Pendergast, Gange, Newton, Lindstrom, Palta & Fisher (1996). An important special case is when repeated measurement occurs at various occasions for each subject, such as in longitudinal studies. A much greater variety of models and fitting methods are available than when a similar survey for repeated ordinal response data was prepared a decade ago (Agresti, 1989). The primary emphasis of the review is on two classes of models, marginal models for which effects are averaged over all clusters at particular levels of predictors, and cluster-specific models for which effects apply at the cluster level. We present the two types of models in the ordinal context, review the literature for each, and discuss connections between them. Then, we summarize some alternative modeling approaches and ways of estimating parameters, including a Bayesian approach. We also discuss applications and areas likely to be popular for future research, such as ways of handling missing data and ways of modeling agreement and evaluating the accuracy of diagnostic tests. Finally, we review the current availability of software for using the methods discussed in this article.     

A forecast simulation analysis of the next‐generation DVD market based on consumer preference data

Just as standards wars over formats had characterized VCRs upon introduction to the market, the next‐generation DVD standards war between Blu‐Ray and HD‐DVD lasted 6 years before Blu‐Ray won the contest. Beginning with stated preference data drawn from a structured conjoint survey conducted before Blu‐Ray became the de facto standard of the next‐generation DVD format, we estimate consumer preferences on digital video players. A Bayesian mixed‐logit model is used and market share simulations are conducted under various scenarios based on the estimated parameters from Bayesian mixed‐logit model to surmise the future South Korean digital video‐player market. Results indicate that consumers feel that network size and title availability are more important than hardware‐related facets of the product, such as definition and storage capacity. The level of title availability and price of the Blu‐Ray player for Blu‐Ray's dominance over DVD will dramatically vary by the penetration rate of DVD players.     

影响自主创新的因素——基于BACE方法对中国省际数据的分析

经典估计贝叶斯平均(BACE)是最近由Sala-i-Martin等人提出的一种处理模型不确定性的方法,它可以在进行参数估计的同时给出各解释变量的稳健性指标,并且还能够按照解释能力的大小对众多的备选变量进行分类和排序.本文首次利用这一方法对可能影响中国自主创新的因素进行了全面的分析,在上百万次回归的基础上,我们得到的主要结果是:在事先列出的20个可能的解释变量中,本地区试验发展支出、人均GDP、贸易依存度、邻接地区试验发展支出对创新产出的解释能力最强,并且都具有良好的稳健性;贷款余额与GDP之比、外商直接投资与GDP之比、各地区科学研究支出、地方财政决算本级收入与GDP之比、邻接地区科学研究支出等五个变量对创新产出也有一定的解释能力.