Maximum Likelihood Methods in Treating Outliers and Symmetrically Heavy-Tailed Distributions for Nonlinear Structural Equation Models with Missing Data

By means of more than a dozen user friendly packages, structural equation models (SEMs) are widely used in behavioral, education, social, and psychological research. As the underlying theory and methods in these packages are vulnerable to outliers and distributions with longer-than-normal tails, a fundamental problem in the field is the development of robust methods to reduce the influence of outliers and the distributional deviation in the analysis. In this paper we develop a maximum likelihood (ML) approach that is robust to outliers and symmetrically heavy-tailed distributions for analyzing nonlinear SEMs with ignorable missing data. The analytic strategy is to incorporate a general class of distributions into the latent variables and the error measurements in the measurement and structural equations. A Monte Carlo EM (MCEM) algorithm is constructed to obtain the ML estimates, and a path sampling procedure is implemented to compute the observed-data log-likelihood and then the Bayesian information criterion for model comparison. The proposed methodologies are illustrated with simulation studies and an example. The research described herein was fully supported by a grant (CUHK 4243/03H) from the Rearch Grants Council of the Hong Kong Special Administration Region. The authors are thankful to the Editor, the Associate Editor, and anonymous reviewers for valuable comments which improve the paper significantly, and are grateful to ICPSR and the relevant funding agency for allowing the use of their data. Requests for reprints should be sent to S. Y. Lee, Department of Statistics, The Chinese University of Hong Kong, Shatin, N. T., Hong Kong.     

临床医生如何应对社会发展对医疗的影响

目前我国的网络及教育均有了长足的进步,信息量迅速增加,信息技术得到了充分的发展,人们获取信息的手段更加便捷,信息不对称较以前有了很大的变化,这些都对医学产生了重大的影响。临床医生必须及时认识到这种变化及发展,及时改变自己的学习、思维及医疗行为模式,这样才能根据不同情况做出最适合的医疗决策,才能更好地履行自己的职责。     

The Substantive Impact of Computers on Philosophy Prolegomena to a Computational and Information-Theoretic Metaphysics

I survey in this article the practical uses of computers in philosophy: except for logic, computers have not yet noticeably improved the quality of philosophizing, research, or pedagogy. They have made work easier. My main interest, however, is in the "substantive" impact that computers may have on philosophical problems, especially in metaphysics. I argue that logic, the notion of decidability, and the theory of computation all predated and did not require modern digital computers. In the philosophy of mind, there has been a persistent conflation of computationalism and physicalism. The two theses can and should be separated. Finally, I suggest that we see glimpses of a new metaphysics based on information and information transformations that goes far beyond the well-trodden mind-brain debates.     

A Computer Scientist's Perspective on Chaos and Mystery

James E. Huchingson's Pandemonium Tremendum draws on a surprisingly fruitful analogy between metaphysics and thermodynamics, with the latter motivated through the more accessible language of communication theory. In Huchingson's model, God nurtures creation by the selective communication of bits of order that arise spontaneously in chaos.     

Television Advertising Disclosures: An Empirical Assessment

Televised advertising disclosures are supposedly designed to supply consumers with important information for decision-making. From the perspective of models of information processing, however, these disclosures may well be improperly conceived and executed. Disclaimers presented in other media are also challenged, though television represents a special case because of consumers' inability to control the processing situation (e.g., to study the disclaimer at length if desired) and because of the extensive use of disclaimers in this medium. In this study, televised advertising disclosures are examined experimentally and found generally to be ineffective. Resultant suggestions for researchers and policy-makers are developed.     

学习不良和优良儿童社会信息加工中反应特点比较

采用情境故事和结构性访谈,研究学习不良和学习优良的小学四年级儿童的社会信息加工特点。结果表明,学习不良儿童在社会信息加工过程中的反应数量与质量总体上不如学习优良儿童;学习优良儿童更能注意到特质线索对他人行为的影响,他们在自我估计时体现了有别于他人的行为倾向,而且具有策略性;学习不良儿童更多地依据情境做出对他人行为的判断,无论是社会判断还是自我估计都还停留在非此即彼的水平上。     

短期学习对陌生面孔认知绩效的影响

本文研究了不同的短期学习时间对陌生面孔的绝对辩认绩效的影响。结果表明：(1)0．5分、1分、5分这三种不同的短期学习时间对陌生面孔的绝对辩认绩效没有明显的影响。(2)人们对人脸结构信息的改变非常敏感,当结构信息变动4．88个象素(或9．13’)时,被试对陌生面孔的平均正确绝对辩认率可达到75％以上。(3)在对陌生人脸的绝对辩认中,被试的正确辩认率随着结构信息变化量的增加而提高,趋势分为快速增长区和迟滞增长区两个区域。     

群际情境下向上社会比较信息对自我评价的影响

以大学生为被试作了两个实验,研究群际情境下向上社会比较信息对自我评价的影响。实验1的结果表明,对于多数派群体的成员来说,来自内群体的向上社会比较信息会提高其自我评价,即产生同化效应,而来自外群体的向上社会比较信息会降低其自我评价,即产生对比效应;对于少数派群体的成员来说,无论向上社会比较信息来自内群体还是外群体,都对其自我评价几乎不产生影响。实验2表明,多数派群体成员在自我评价上的内群体同化效应依赖于群际对比。     

顿悟认知机制的研究述评与理论构想

顿悟是创造性思维的主要形式,它一直以来都是心理学家感兴趣的研究课题。该文对有关顿悟认知机制的现象学描述作了介绍,比较了表征转变与进程监控两种认知观点,探讨了初级加工与顿悟认知机制间的关系。初步提出了顿悟问题解决中原型激活及其启发信息质量的理论假说,对未来研究做出了设想,以期能最终揭示出顿悟的内部发生机制。