一种新的灰色绝对关联度模型及其应用

为了处理序列曲线间的负相关等问题,并使关联满足一定的性质,基于灰色关联分析的基本思想,本文利用数列曲线的平均相对变化态势构建了一种新的灰色绝对关联度模型,并探讨了模型的唯一性、对称性、相似性、平行性、一致性等性质,而后以新模型对我国及各省市区产业结构的有序度进行了测算,结果表明新模型计算简单,计算量小,更与实际相符。     

Moral dialogs and public opinion research

Etzioni’s article is thought provoking, and contains a series of arguments that would be useful lines of inquiry for scholars of public opinion. In many ways, these ideas link to, and can enrich existing areas of research on opinion formation, opinion change, and political behavior more broadly. Specifically, the elite vs. mass nature of these dialogs, the extent to which they are actual political discussions, and the impact of polarization on them are avenues where these ideas can inform broader understandings of public opinion, and vice versa. Etzioni’s arguments about the role of morals in political discussion and as agents of opinion change warrant further inquiry.     

Comparative GMM and GQL logistic regression models on hierarchical data

We often rely on the likelihood to obtain estimates of regression parameters but it is not readily available for generalized linear mixed models (GLMMs). Inferences for the regression coefficients and the covariance parameters are key in these models. We presented alternative approaches for analyzing binary data from a hierarchical structure that do not rely on any distributional assumptions: a generalized quasi-likelihood (GQL) approach and a generalized method of moments (GMM) approach. These are alternative approaches to the typical maximum-likelihood approximation approach in Statistical Analysis System (SAS) such as Laplace approximation (LAP). We examined and compared the performance of GQL and GMM approaches with multiple random effects to the LAP approach as used in PROC GLIMMIX, SAS. The GQL approach tends to produce unbiased estimates, whereas the LAP approach can lead to highly biased estimates for certain scenarios. The GQL approach produces more accurate estimates on both the regression coefficients and the covariance parameters with smaller standard errors as compared to the GMM approach. We found that both GQL and GMM approaches are less likely to result in non-convergence as opposed to the LAP approach. A simulation study was conducted and a numerical example was presented for illustrative purposes.     

Some results for maximum likelihood estimation of adjusted relative risks

Maximum likelihood (ML) estimation of relative risks via log-binomial regression requires a restricted parameter space. Computation via non linear programming is simple to implement and has high convergence rate. We show that the optimization problem is well posed (convex domain and convex objective) and provide a variance formula along with a methodology for obtaining standard errors and prediction intervals which account for estimates on the boundary of the parameter space. We performed simulations under several scenarios already used in the literature in order to assess the performance of ML and of two other common estimation methods.     

Measuring Dynamic Capabilities: Practices and Performance in Semiconductor Manufacturing

Research on dynamic capabilities emphasizes the importance and role of organizational routines in explaining interfirm differences in performance. While performance differences are well documented, few empirical analyses explore the processes inside organizations that lead to dynamic capabilities or attempt to define and measure their performance effects. This paper examines one type of dynamic capability – the development and introduction of new process technologies in semiconductor manufacturing. This dynamic capability is an important source of competitiveness in the semiconductor industry, given the short product lifecycles, rapid price declines, and rapid technological advances that define the industry. Because much of the knowledge that underpins semiconductor manufacturing is idiosyncratic, firm-level R&D organization and information technology practices that facilitate problem solving and learning-based improvement provide important and enduring advantages. We derive models of the rate of improvement in manufacturing yield (i.e. the quality of production) and cycle time (i.e. the speed of production) following the development and introduction of new process technologies in manufacturing facilities, and test the empirical specifications of these models. The ways in which semiconductor manufacturers accumulate experience and articulate and codify knowledge within the manufacturing environment build new process development and introduction dynamic capabilities that improve performance.     

The enduring allure of charisma: How Barack Obama won the historic 2008 presidential election

We apply charismatic leadership theory to the historic 2008 United States presidential election, in hopes of inspiring dialogue around how leadership theory can inform the critical process of evaluating and electing public leaders. While numerous leadership theories are relevant to understanding the 2008 election, charismatic leadership theory highlights aspects of the leader, followers, and the unfolding economic crisis that are particularly relevant in helping us to understand how a relatively inexperienced political outsider ascended to the US Presidency. Given the potential perils and challenges newly elected President Barack Obama faces in the months and years ahead, we also suggest four core strategies rooted in charismatic leadership theory that may help him capitalize on his early charismatic appeal, as well as avoid the pitfalls of charisma that have plagued some of his predecessors.     

Comparing Acquisition of Exchange-Based and Signed Mands With Children With Autism

Therapists and educators frequently teach alternative-communication systems, such as picture exchanges or manual signs, to individuals with developmental disabilities who present with expressive language deficits. Michael (1985) recommended a taxonomy for alternative communication systems that differentiated between selection-based systems in which each response is topographically identical (e.g., card selection and exchange systems) and topography-based systems in which each response is topographically distinct (e.g., signed language). We compared the efficiency of training picture exchanges and signs with 3 participants who presented with severe language deficits; all participants acquired the picture-exchange responses more readily.     

Teaching Note—Description and Preliminary Evaluation of a Modified College Experience for Adults With Intellectual and Developmental Disabilities

ABSTRACT

This article describes the implementation and preliminary evaluation of a modified college experience for adults with intellectual and developmental disabilities (IDD) at a small liberal arts college. To increase social work students’ interest in working with this population and access of people with IDD to higher education, Bridges to Skidmore was founded in 2010 as a low-cost method for providing cooperative learning opportunities for students and individuals with IDD. Preliminary evaluation reveals that participation can change students’ attitudes toward those with IDD, which may increase their intention to work with this population in the future. The program has created an enriching experience for the college students, lecturing professors, and adults with IDD, and can be easily replicated on other campuses.     

A Short Form of the Trauma Symptom Checklist for Young Children

A short form of the Trauma Symptom Checklist for Young Children was derived from the original 90 items. An exploratory factor analysis of each factor identified the four items from each of the original factors with the highest eigenvalues. These items were subjected to confirmatory factor analysis. The best fit was obtained for an 8-factor, 32-item model. The short form evidenced good convergent validity with parent ratings obtained from the Child Behavior Checklist, the Child Sexual Behavior Inventory, and the University of California at Los Angeles Post-traumatic Stress Disorder Reaction Index (UCLA PTSD RI). Norms (t-scores and percentiles based on raw scores) were calculated by age and by gender. The short form has promise as a screening measure with parents in settings like a child advocacy center.