An Efficient MCMC Algorithm to Sample Binary Matrices with Fixed Marginals

Uniform sampling of binary matrices with fixed margins is known as a difficult problem. Two classes of algorithms to sample from a distribution not too different from the uniform are studied in the literature: importance sampling and Markov chain Monte Carlo (MCMC). Existing MCMC algorithms converge slowly, require a long burn-in period and yield highly dependent samples. Chen et al. developed an importance sampling algorithm that is highly efficient for relatively small tables. For larger but still moderate sized tables (300×30) Chen et al.’s algorithm is less efficient. This article develops a new MCMC algorithm that converges much faster than the existing ones and that is more efficient than Chen’s algorithm for large problems. Its stationary distribution is uniform. The algorithm is extended to the case of square matrices with fixed diagonal for applications in social network theory. I am indebted to my colleague Gunter Maris for his suggestion to add a Metropolis–Hastings step as the finishing touch of the algorithm.     

贝叶斯网在认知诊断属性层级结构确定中的应用

K. K. Tatsuoka和她同事研究的规则空间模型(RSM)是一种在国内外有较大影响的认知诊断模型, 但是Tatsuoka的RSM是由学科专家先从已编制的测验中抽取出属性, 然后给出测验的关联Q阵, 再由该Q阵导出属性间的层级关系。已有研究证明, 这种做法所得到的属性间的层级关系难以保证是正确的, 甚至难以保证属性间的层级关系是唯一确定的。这里利用贝叶斯网进行结构学习, 从被试的属性掌握模式中挖掘出属性间的层级关系, 学习所得到的层级关系可以用来验证由RSM中的方法得到的层级关系。模拟实验和实证研究的结果都显示了该方法所得到的属性层级关系是有参考价值的, 可以为命题或测量专家带来有用的信息。     

The Impact of Individual and Interpersonal Factors on Perceived News Media Bias

A large percentage of the public believes that the news media are biased, and the majority of these individuals consider the direction of bias to be against their own viewpoints. Past research has examined how individual factors such as strength of partisanship or extent of political involvement heighten bias perceptions, but little attention has been paid to interpersonal factors such as the ideological similarity or dissimilarity of personal communication networks. Results of a national survey show that perceptions of media bias were unrelated to the overall amount of discussion but were positively related to conversations with ideologically like–minded individuals. Moreover, the impact of conversations with similar others was stronger among Republicans than among Democrats, a finding consistent with recent work on news self–coverage of media bias claims.     

Effects of Friendship Circles on the Social Interactions of Elementary Age Students with Mild Disabilities

This study assessed the effects of Friendship Circles on the social interactions between students with mild disabilities and their nondisabled peers. A multiple probe design was used to analyze the social interactions during lunch. Data also were collected in the form of sociograms and anecdotal records. In addition, generalization was assessed during recess observations. Results indicated that the Friendship Circle intervention produced increases in appropriate interactions at lunch for all three students and for two there were increases in friendly play at recess. Anecdotal data suggested improved social interactions for two of the students throughout the day and improved social behaviors in the general education classroom such as cooperation during group activities. Implications for future research are discussed.     

Radical psychology networks: a review and guide

Movements of psychologists with a liberatory agenda have emerged in a number of countries. A guide and overview is offered here. These networks have not yet developed into a particularly strong movement. Some of the reasons for this will be discussed in relation to the contradictory role of mainstream psychology as both loyal critic and as resource for the ruling order. Copyright © 2004 John Wiley & Sons, Ltd.     

Inner-City Children Living with an HIV-Seropositive Mother: Parent–Child Relationships, Perception of Social Support, and Psychological Disturbance

Despite ongoing concern about the well-being of HIV-seronegative children living in urban poverty with a seropositive mother, very little is known about this expanding population of children. In this cross-sectional study, the psychosocial adjustment of 60 ethnic minority children 11 to 16 years of age who were living with an HIV-seropositive mother was compared with that of 108 children attending public school in the same community. Results of three multivariate analyses of covariance indicated that, after allowance for differences associated with age, gender, ethnicity, and family structure, the HIV-affected group confirmed (a) greater disturbance in the parent–child relationship, (b) less social support, and (c) greater disturbance in psychological functioning. Secondary analysis of the multivariate findings indicated that the differences were characterized primarily by (a) perception of more indifference and hostility in the mother–child relationship, (b) perception of less social support available from parents, friends, and teachers, and (c) less self-esteem. The findings suggest that HIV infection and concurrent problems may compromise parent–child relationships and perception of social support in ways that leave older, seronegative children living with an infected mother at risk for psychological disturbance.     

Mathematical foundations of consciousness

We employ the Zermelo–Fränkel Axioms that characterize sets as mathematical primitives. The Anti-foundation Axiom plays a significant role in our development, since among other of its features, its replacement for the Axiom of Foundation in the Zermelo–Fränkel Axioms motivates Platonic interpretations. These interpretations also depend on such allied notions for sets as pictures, graphs, decorations, labelings and various mappings that we use. A syntax and semantics of operators acting on sets is developed. Such features enable construction of a theory of non-well-founded sets that we use to frame mathematical foundations of consciousness. To do this we introduce a supplementary axiomatic system that characterizes experience and consciousness as primitives. The new axioms proceed through characterization of so-called consciousness operators. The Russell operator plays a central role and is shown to be one example of a consciousness operator. Neural networks supply striking examples of non-well-founded graphs the decorations of which generate associated sets, each with a Platonic aspect. Employing our foundations, we show how the supervening of consciousness on its neural correlates in the brain enables the framing of a theory of consciousness by applying appropriate consciousness operators to the generated sets in question.     

Building International Collaborative Capacity: Contributions of Community Psychologists to a European Network

Europe is in the process of building a more participative, just, and inclusive European Union. The European Social Fund, which is an initiative developed to actively promote multinational partnerships that address pressing social issues, is a good example of the European transformation. This article describes the steps taken to develop and evaluate the activities of an international network promoting collaborative capacity among regional partners involved in the prevention of labor discrimination toward immigrants in three European countries—Spain, Belgium, and Italy. An international team of community psychologists proposed an empowering approach to assess the collaborative capacity of the network. This approach consisted of three steps: (1) establishing a collaborative relationship among partners, (2) building collaborative capacity, and (3) evaluating the collaborative capacity of the network. We conclude with lessons learned from the process and provide recommendations for addressing the challenges inherent in international collaboration processes.     

It is Better to Receive than to Give: Advice Network Effects on Job and Work-Unit Attachment

Purpose  The purpose of this paper was to investigate the relationship between advice-giving, advice-receiving, and employee work attitudes. We argue that (1) both advice-receiving and advice-giving will be positively related to job involvement; (2) advice-receiving will be more strongly associated with work-unit commitment than advice-giving; and (3) job involvement will mediate the relationship between advice-receiving and work-unit commitment. Design/methodology/approach  We conducted an empirical study of admissions department employees at a large university in southwest Pennsylvania in the United States. Respondents completed surveys which included questions related to demographics, social network ties, and attitudes. Findings  We found that while advice-giving and advice-receiving were positively related to job involvement, only advice-receiving was positively related to work-unit commitment. Job involvement fully mediated the relationship between advice-receiving and work-unit commitment. Implications  Our study (1) shows that advice-giving and advice-receiving are related to important work-related attitudes in organizations; (2) highlights the importance of the directionality of advice flow, as employees who received as opposed to provided advice tended to have higher levels of work-unit commitment; and (3) demonstrates that social network ties were related to work-unit attachment through job involvement. Originality/value   We examine job involvement and work-unit commitment using a social network analysis thus providing new insights about the relationships between advice-giving, advice-receiving and these important variables. An earlier version of this paper won the Best Paper Award at the 2005 Southwest Academy of Management Conference. The authors would like to dedicate this paper to Margie Jonnet.     

Evidence and inference in educational assessment

Educational assessment concerns inference about students' knowledge, skills, and accomplishments. Because data are never so comprehensive and unequivocal as to ensure certitude, test theory evolved in part to address questions of weight, coverage, and import of data. The resulting concepts and techniques can be viewed as applications of more general principles for inference in the presence of uncertainty. Issues of evidence and inference in educational assessment are discussed from this perspective.Probability isn't really about numbers; it's about the structure of reasoning.Presidential address to the Psychometric Society, presented June 25, 1994, in Champaign, Illinois.Supported by (1) Contract No. N00014-91-J-4101, R&T 4421573-01, from the Cognitive Science Program, Cognitive and Neural Sciences Division, Office of Naval Research, (2) the National Center for Research on Evaluation, Standards, Student Testing (CRESST), Educational Research and Development Program, cooperative agreement number R117G10027 and CFDA catalog number 84.117G, as administered by the Office of Educational Research and Improvement, U.S. Department of Education, and (3) the Statistical and Psychometric Research Division of Educational Testing Service. I am grateful for comments and suggestions from Henry Braun, Drew Gitomer, Richard Patz, Jonathan Troper, and Howard Wainer.