Bayesian Hypothesis Testing: a Reference Approach

For any probability model M={p(x|θ, ω), θεΘ, ωεΩ} assumed to describe the probabilistic behaviour of data xεX, it is argued that testing whether or not the available data are compatible with the hypothesis H₀={θ=θ₀} is best considered as a formal decision problem on whether to use (a₀), or not to use (a₀), the simpler probability model (or null model) M₀={p(x|θ₀, ω), ωεΩ}, where the loss difference L(a₀, θ, ω) –L(a₀, θ, ω) is proportional to the amount of information δ(θ₀, ω), which would be lost if the simplified model M₀ were used as a proxy for the assumed model M. For any prior distribution π(θ, ω), the appropriate normative solution is obtained by rejecting the null model M₀ whenever the corresponding posterior expectation ∫∫δ(θ₀, θ, ω)π(θ, ω|x)dθdω is sufficiently large. Specification of a subjective prior is always difficult, and often polemical, in scientific communication. Information theory may be used to specify a prior, the reference prior, which only depends on the assumed model M, and mathematically describes a situation where no prior information is available about the quantity of interest. The reference posterior expectation, d(θ₀, x) =∫δπ(δ|x)dδ, of the amount of information δ(θ₀, θ, ω) which could be lost if the null model were used, provides an attractive nonnegative test function, the intrinsic statistic, which is invariant under reparametrization. The intrinsic statistic d(θ₀, x) is measured in units of information, and it is easily calibrated (for any sample size and any dimensionality) in terms of some average log‐likelihood ratios. The corresponding Bayes decision rule, the Bayesian reference criterion (BRC), indicates that the null model M₀ should only be rejected if the posterior expected loss of information from using the simplified model M₀ is too large or, equivalently, if the associated expected average log‐likelihood ratio is large enough. The BRC criterion provides a general reference Bayesian solution to hypothesis testing which does not assume a probability mass concentrated on M₀ and, hence, it is immune to Lindley's paradox. The theory is illustrated within the context of multivariate normal data, where it is shown to avoid Rao's paradox on the inconsistency between univariate and multivariate frequentist hypothesis testing.     

中国房地产市场财富效应分析——基于生命周期假说的宏观消费函数

在生命周期假说的基础上,构造了一个城镇居民资产与城镇居民人均消费关系的模型,并利用1978~2006年的数据,分阶段实证研究了中国城镇居民住宅资产对城镇居民人均消费的影响。实证研究发现,中国房地产市场不具有财富效应。中国消费者的消费心理、法律制度以及现阶段中国房地产市场不成熟,是造成中国房地产市场不具有财富效应的重要原因。     

情感因素对TEFL的影响及对策研究

情感因素是影响TEFL的重要因素之一。在外语教学中如何运用积极的情感策略以提高外语教学的效果十分重要。本文以克拉申(Krashen)的情感过滤假说(the Affective Filter Hypothesis)理论为基础,归纳了影响TEFL的主要情感制约因素,并探究克服这些制约的策略。     

MAXIMUM-LIKELIHOOD ESTIMATES OF A US MULTIREGIONAL HOUSEHOLD EXPENDITURE SYSTEM

This paper applies the maximum-likelihood equation to a model that produces US regional household expenditure estimates using national-level data on average expenditures by type of household and regional data on the number of households by type. Empirical results follow the analytical properties of the model and demonstrate an impressive capacity to recover regional statistics. These findings are useful in applied regional studies since they demonstrate a general framework to assess the input data and the overall estimation model.     

全新范式方法在传统语言学研究中的应用

在对乔姆斯基的转换生成语法进行全面概述的基础上,指认出其对传统语言学研究范式所进行的三大转换,即从描述到解释,从表层到深层以及从解构到建构,而这种转换的实质则在于从经验到先验。     

中国国民经济若干指标季节波动的方向数据统计分析

本文应用方向数据统计方法分析1998～2005年货运量、居民消费价格总指数、社会消费品零售总额、出口总额和进口总额以及1999～2005年工业增加值等指标的月度数据。通过均匀性检验和Von-Mises分布检验确定分布类型，分析不同分布类型下经济指标的波动特征，从理论上探讨季节波动的成因。指出有良性规律的季节波动是实现既稳定又较快经济增长的保证。     

财会“主体”类型及其关系

基于会计主体假设中对会计主体的质疑、财务主体研究中对财务主体的争议,理财主体假设中理财主体的悄然出现,分析了财会主体的三个类型及其三者之间的交叉关系和主客体关系。     

Nonlinear dynamical structural equation models

Structural equation models (SEMs) have been widely used in behavioural, educational, medical and socio-psychological research for exploring and confirming relations among observed and latent variables. In the existing SEMs, the unknown coefficients in the measurement and structural equations are assumed to be constant with respect to time. This assumption does not always hold, as the relation among the observed and latent variables varies with time for some situations. In this paper, we propose nonlinear dynamical structural equation models to cope with these situations, and explore the nonlinear dynamic of the relation between the variables involved. A local maximum likelihood-based estimation procedure is proposed. We investigate a bootstrap resampling-based test for the hypothesis that the coefficient is constant with respect to time, as well as confidence bands for the unknown coefficients. Intensive simulation studies are conducted to show the empirical performance of the proposed estimation procedure, hypothesis test statistic and confidence band. Finally, a real example in relation to the stock market of Hong Kong is presented to demonstrate the proposed methodologies.