Bayesian analysis of mixture modelling using the multivariate t distribution

A finite mixture model using the multivariate t distribution has been shown as a robust extension of normal mixtures. In this paper, we present a Bayesian approach for inference about parameters of t-mixture models. The specifications of prior distributions are weakly informative to avoid causing nonintegrable posterior distributions. We present two efficient EM-type algorithms for computing the joint posterior mode with the observed data and an incomplete future vector as the sample. Markov chain Monte Carlo sampling schemes are also developed to obtain the target posterior distribution of parameters. The advantages of Bayesian approach over the maximum likelihood method are demonstrated via a set of real data.     

错误的繁盛:复辟笼罩下之大众文化探析——以"文明戏"为案例

本文从大众文化的视角,选取了一段典型的时期、一个典型的案例,来探讨娱乐和政治、精英文化与大众文化的关系.尽管政治波谲云诡,但并未阻断上海日渐兴起的大众文化发展之链条,"文明戏"是其一首要环节.娱乐疏离于政治,却又包含颠覆政治的因素.走出古典之后的知识人,就部分被吸引到大众文化的制造之中.在各种文化冲突中,"文明戏"成为替罪羔羊,被不断地想象和重构.     

Significant Factors of Aviation Insurance and Risk Management Strategy: An Empirical Study of Taiwanese Airline Carriers

Aviation insurance premiums have become a heavy burden for the airline industry since September 11, 2001. Although the industry must constantly balance its operations between profitability and safety, the reality is that airlines are in the business of making money. Therefore, their ability to reduce cost and manage risk is a key factor for success. Unlike past research, which used subjective judgment methods, this study applied quantitative historical data (1999–2000) and gray relation analysis to identify the primary factors influencing ratemaking for aviation insurance premiums. An empirical study of six airlines in Taiwan was conducted to determine these factors and to analyze the management strategies used to deal with them. Results showed that the loss experience and performance of individual airlines were the key elements associated with aviation insurance premiums paid by each airline. By identifying and understanding the primary factors influencing ratemaking for aviation insurance, airlines will better understand their relative operational strengths and weaknesses, and further help top management identify areas for further improvement. Knowledge of these factors combined with effective risk management strategies, may result in lower premiums and operating costs for airline companies.     

从贵州省第六届民运会看贵州少数民族体育的发展

通过对贵州省第六届民运会的实地调查及与历届全国民运会和贵州省民运会的比较分析,并提出了值得思考的对策,旨在促进贵州少数民族体育的发展,为当好第九届全国民运会东道主做好准备.     

论苗族刺绣及其传承

苗族刺绣已被列入首批国家级非物质文化遗产，具有鲜明的艺术特色，但由于受传承方式等的影响，苗绣有濒临失传危机。因此，必须采取多种措施，强化苗绣的保护传承和开发利用。     

广西北部湾经济区打造增长新一极优势依托分析

优势依托理论演进表明,经济的又好又快增长取决于综合优势的发挥,而综合优势的发挥更意味着在发挥比较优势的基础上,一要改进交易效率(如制度创新),二要提高竞争优势(首先是技术创新、其次才是产业升级)。因此,广西北部湾经济区打造经济增长新一极绝不能再走我国沿海发达地区曾经走过的路子,即绝不能再采用那种依赖资源禀赋比较优势的粗放的代工增长模式,只能采用依托于综合优势的新增长模式。     

A Semi-parametric Regression Model with Errors in Variables

Abstract.  In this paper, we consider a partial linear regression model with measurement errors in possibly all the variables. We use a method of moments and deconvolution to construct a new class of parametric estimators together with a non-parametric kernel estimator. Strong convergence, optimal rate of weak convergence and asymptotic normality of the estimators are investigated.     

小额信贷之违约概率模型:特别考虑异质性

在新巴塞尔资本协议(New Basel Capital Accord)对金融全球化的冲击及金融机构改善资产质量及合并政策的影响下,我国台湾地区金融业进入激烈合并竞争的时代.许多银行颇受降低逾放比率及增加净值报酬率与资产报酬率两难之困扰.消费性信用贷款产品利差大、风险分散,是金融机构授信经营极重要的产品.实证结果显示,采用世代研究(cohort study)建立之模型对样本数据之拟合程度较个案对照研究法(case-control study)的解释变异量为佳,且较符合新巴塞尔资本协议规定及科学程序.虽然Logistic 回归模型在建立逾期概率模型上广泛地被使用,但要求存在于同构型的变异数Var=np(1-p)假设上,且在数据分析上常因为出现变异数之异质性问题,故可采用调整变异数异质性之方法.     

提高企业家物质激励水平的理论思考

企业家作为社会阶层一特殊群体,必须取得与其业绩相对应的报酬。文章试图从委托-代理理论、人力资本理论、新古典经济增长理论和能力本位制理论等视角分析提高企业家物质激励现有水平的必要性。     

地区信息化水平的综合评价

本文从信息化的发展入手,阐述了信息化建设及各地区信息化水平评价的重要性,采用多元统计中的主成分分析和主成分回归法,设计一个综合指标用以评估各类地区的信息化水平及其在全国所处的位置,指导各地区的信息化建设。