Ridge estimation in regression problems with autocorrelated errors: A monte carlo study

This paper presents the results of a Monte Carlo study of OLS and GLS based adaptive ridge estimators for regression problems in which the independent variables are collinear and the errors are autocorrelated. It studies the effects of degree of collinearity, magnitude of error variance, orientation of the parameter vector and serial correlation of the independent variables on the mean squared error performance of these estimators. Results suggest that such estimators produce greatly improved performance in favorable portions of the parameter space. The GLS based methods are best when the independent variables are also serially correlated.     

Autoregressive processes applied to acceptance sampling by varlables

The effect of serial correlation on acceptance sampling plans by variables has been examined in this paper assuming the quality measurements follow an AR(p) process. The effect of serial correlation can be examined by comparing OC curves, sample size and producer's risks, ∝, with that of the independent case when the process standard deviation, σ, is known. When σ is unknown and for large n, sampling plans can be constructed using the central limit theorem. However, for σ unknown and for small n, there is no satisfactory method of obtaining sampling plans.     

From Conditional Independence to Conditionally Negative Association: Some Preliminary Results

Conditional moment estimates on the cumulative sum of conditionally independent random variables are derived, conditional prophet inequalities for conditionally independent random variables are established, a comparison theorem on conditional moment inequalities between conditionally independent and conditionally negatively associated random variables is established. As applications of these results, a conditional Rosenthal type inequality and two conditional Kolmogorov exponential inequalities for conditionally negatively associated random variables are obtained.     

Convergence rates and powers of six power-divergence statistics for testing independence in 2 by 2 contingency table

Several tests for testing independence of 2 by 2 contingency tables have been proposed over the years. Cressie and Read (1984) identified several of these tests as members of a power-divergence family, and much of the characteristics for these tests are unified. However, the question of which test is best is still not fully understood. This paper provides algorithms for chi-square estimates and investigates the convergence rates and powers of these chi-square tests.     

A Useful Property of Some Symmetric Statistics

The distributions of some statistics arising from the comparison of two populations share a common structure. Consequences of this structure are derived and their usefulness indicated. The examples of statistics to which the theory applies include various correlation coefficients.     

论我国当下语境中的法官独立审判

司法独立和法官独立审判是案件得到公正审判的前提条件.我国当下法官独立审判遇到的种种障碍性因素与法官本身缺乏主体性资格有关.尽管司法独立既是法官争取的结果,也是法学和政治哲学发展的产物,但是法官在这一改革过程中还是应该有所作为的.如此,才能把法官独立审判逐步推向现实化.这就需要法官从四个方面来增强自己的内动力,这种内动力是法官能够坚持独立审判的主体性资格能力:守法精神、敬业精神、大的智慧、勤勉工作,而第一种素养又是基础素养,是法官成为法官的基本要求.     

试论上古汉语连动式中的连词问题

上古汉语连词用于连动式是十分常见的现象。从《尚书》到《左传》到《史记》,连词数量呈逐渐增加的趋势,但连动式中连词的使用频率则经历了从少到多再到少的过程。连词在上古连动式有语法、语用和语义三个方面的功用,其使用频率的变化则存在连动式语法化等方面的原因。     

实施审判独立原则之辨思

审判独立是一项宪法原则,该原则的落实对发展社会主义市场经济、民主政治和文化建设都具有重要的意义。实现审判独立,不只是宪法条文的规定,也是联系着各种复杂因素的社会问题,我们应该立足于中国的实际,抛弃非此即彼的简单思维,运用辨证法,使对立着的矛盾双方走向统一。实施审判独立原则,要处理好以下几对关系:大局着眼与小处入手、保持独立与以退为进、接受监督与树立权威、选用良才与充分保障、消极独立与积极独立、群众满意与终局裁决、法院独立与法官独立、制度创新与强化管理。     

审计质量低劣的原因及对策研究

目前国内外大量审计丑闻表明审计质量低劣已经成为一个国际问题。利用经济学的“逆向选择”和“道德风险”理论能够更加深刻的分析其问题产生的内在制度原因。并从政府和行业两个方面加强监督管理,强化注册会计师的民事责任。     

纯文学观与近代小说观念的曲折演进

近代诗文化的衰竭和小说文化的张扬,推动近代崇高艺术的发展。小说维度纯文学观的审美超越性,形成其区别于通俗小说的显著的时代特征。对小说本质的认定,是纯文学观终极关怀的突出表现。近代纯文学观的小说维度建构,展示了新小说家追求小说文体独立的文学批评进路,并体现出中国小说观念自身的矛盾和新小说家文体探究的曲折。中国小说观念的近代转型,在祛杂存纯的文学追求中抒写一代学人观念建构的曲折演进轨迹。