On model selection in Bayesian regression

We discuss the problem of constructing a suitable regression model from a nonparametric Bayesian viewpoint. For this purpose, we consider the case when the error terms have symmetric and unimodal densities. By the Khintchine and Shepp theorem, the density of response variable can be written as a scale mixture of uniform densities. The mixing distribution is assumed to have a Dirichlet process prior. We further consider appropriate prior distributions for other parameters as the components of the predictive device. Among the possible submodels, we select the one which has the highest posterior probability. An example is given to illustrate the approach.     

“入库规则”辨析

“入库规则”是债权代位权制度中的规则之一。它不仅可以保障行使代位权的债权人的利益,同时还能顾及其他债权人的利益。但这种理想的债权担保制度,在现实实践中效果并不理想。因此,从经济效益、法理等视角出发,“优先权规则”取代“入库规则”不仅合理,而且合法。     

Common priors under incomplete information: a unification

Summary. While the meaningfulness of the common prior assumption (CPA) under incomplete information has been established recently by various authors, its epistemic rationale has not yet been adequately clarified. To do so, we provide a characterization of the CPA in terms of a new condition called “Mutual Calibration”, and argue that it constitutes a more transparent and more primitive formalization of the Harsanyi Doctrine than the existing characterizations. Our analysis unifies the understanding of the CPA under incomplete information and clarifies the role of higher-order expectations and of the difference between situations with only two and those with at least three agents. In the concluding section, the analysis is applied to the problem of defining Bayesian consistency of the intertemporal beliefs of a single-agent with imperfect memory. The CPA yields a notion of “Bayesian updating without a prior”. Received: March 24, 2000; revised version: April 27, 2000     

Stochastic loss reserving: A new perspective from a Dirichlet model

Forecasting the outstanding claim liabilities to set adequate reserves is critical for a nonlife insurer's solvency. Chain–Ladder and Bornhuetter–Ferguson are two prominent actuarial approaches used for this task. The selection between the two approaches is often ad hoc due to different underlying assumptions. We introduce a Dirichlet model that provides a common statistical framework for the two approaches, with some appealing properties. Depending on the type of information available, the model inference naturally leads to either Chain–Ladder or Bornhuetter–Ferguson prediction. Using claims data on Worker's compensation insurance from several U.S. insurers, we discuss both frequentist and Bayesian inference.     

Welfare Losses Due to Livestock Grazing on Public Lands: A Count Data Systemwide Treatment

Backcountry hikers' willingness-to-pay for removing grazing from trails in the Hoover Wilderness is analyzed using a multinomial Dirichlet negative binomial distribution. This multivariate discrete distribution allows the direct calculation of seasonal welfare measures that are derived from an incomplete demand specification. The welfare maximizing choice of activities is examined on a trail-by-trail basis using the results of the analysis. Our findings suggest that a mix of hiking and grazing activities provide the greatest social welfare.     

Why Seniors use Mobile Devices: Applying an Extended Model of Goal-Directed Behavior

Seniors’ use of mobile devices for tourism-related purposes is an emerging social trend, but there is little theoretically based research on the topic. This study examines seniors’ usage of mobile devices for tourism-related purposes, applying the extended model of goal-directed behavior. Usefulness and enjoyment are shown to have significant effects on seniors’ use of mobile devices for tourism purposes and prior knowledge of information technology has a significant impact on seniors’ desire and behavioral intention to use mobile devices for tourism-related purposes. This study offers theoretical and practical contributions to tourism academics and practitioners.     

Bayes estimates of muIti-criteria decision alternatives using Monte Carlo integration

A Bayesian procedure is proposed for the estimation of the weights of the alternatives in a multi-criteria decision model with data that stem from pair-wise comparison of alternatives. The prior information restricts the weights to the unit simplex. The posterior results are computed by Monte Carlo integration procedures based on importance sampling. The Bayesian procedure is applied to a case study concerning the choice of a professor of Operations Research (OR). Results are: (1) according to the Bayesian procedure a different candidate would be chosen as professor of OR than according to the maximum likelihood procedure; (2) given the prior and data information, there exists a substantial probability of taking the wrong decision; (3) there exists a ranking of the candidates with a posterior probability greater than one half.     

Nonparametric Bayes inference for concave distribution functions

Bayesian inference for concave distribution functions is investigated. This is made by transforming a mixture of Dirichlet processes on the space of distribution functions to the space of concave distribution functions. We give a method for sampling from the posterior distribution using a Pólya urn scheme in combination with a Markov chain Monte Carlo algorithm. The methods are extended to estimation of concave distribution functions for incompletely observed data.     

应用加权高斯模型的非理想稀疏信道估计

在高速通信系统中,由于多径信道通常存在一些小的散射体,使得抽头向量不满足理想的稀疏特性,导致经典的稀疏估计算法存在一定的性能损失。针对上述非理想稀疏特性问题,提出了一种基于酉变换近似消息传递（Unitary Transform Approximate Message Passing,UT-AMP）和加权高斯（Weighting-Gaussian,WG）先验模型的稀疏估计算法。首先,由非理想稀疏信道的构造分析,导出了WG先验模型和参数;其次,利用贝叶斯公式对正交频分复用(Orthogonal Frequency Division Multiplexing,OFDM)系统进行因式分解和因子图建模,归纳了在消息传递框架内期望最大化（Expectation Maximization,EM）算法嵌入方式,推导了联合UT-AMP和EM的信道估计算法;最后,建立仿真环境对所提算法进行复杂度分析和数值仿真。仿真结果表明,所提算法能够以同阶复杂度实现信道估计性能和频带利用率的提升,具有很高的应用和推广价值。     

先验知识对创业机会识别的影响研究——风险感知的调节作用

本文首先界定了先验知识、创业机会识别和风险感知的内涵,然后,基于创业相关理论、情绪相关理论及激励理论,提出先验知识与创业机会识别正相关及风险感知对二者的关系具有负向调节作用的研究假设,并从浙江、天津、山东等几个省市进行抽样调查,采用多元线性回归分析方法对获得的216份有效问卷进行统计分析,实证分析结果支持了文章的研究假设。