Recovery of inter-block information: extensions in a two variance component model

For a two variance component mixed linear model, it is shown that under suitable conditions there exists a nonlinear unbiased estimator that is better than a best linear unbiased estimator defined with respect to a given singular covariance matrix. It is also shown how this result applies to improving on intra-block estimators and on estimators like the unweighted means estimator in a random one-way model.     

A cumulative ecological–transactional risk model of child maltreatment and behavioral outcomes: Reconceptualizing early maltreatment report as risk factor

The current analysis was designed to critically examine the tendency to focus on child maltreatment as a unique risk factor and test the resulting assumption of a direct causal relationship between early maltreatment and later behavioral problems. The variation seen in behavioral outcomes among children reported for maltreatment early in life led us to hypothesize that the cumulative level of risk facing children and their families can, at least in part, account for that variation in outcome. Participants were 242 mothers of predominantly at-risk newborn infants who were interviewed shortly after giving birth. The State Central Registry of Maltreatment was then reviewed over each child's first four years of life to assess for early maltreatment. Following the neonatal interviews, mothers completed the Child Behavior Checklist when their children were 4, 6, 8, 10 and 12 years-of-age. Although early maltreatment report does appear to be important to early child functioning, the cumulative level of risk more strongly predicts long-term clinical behavioral difficulty. High-risk children who were not reported for maltreatment by age 4 demonstrate greater behavioral problem trajectories than did low-risk children with a maltreatment report. Maltreatment itself may be best conceptualized as an important, but not singularly so, risk factor for later behavioral problems. In focusing directly on reported maltreatment, our child protective systems may be paying too little attention to what else is going wrong in the lives of children and targeting intervention efforts in the wrong direction. When it comes to early maltreatment our child protective policy and practice need to broaden their lenses to include greater emphasis on overall family functioning, stress and well-being. Early maltreatment, it seems, may be a symptom of more profound problems in the early environments of our most vulnerable children, rather than the problem itself.     

Orthodox BLUP versus h-likelihood methods for inferences about random effects in Tweedie mixed models

Recently, the orthodox best linear unbiased predictor (BLUP) method was introduced for inference about random effects in Tweedie mixed models. With the use of h-likelihood, we illustrate that the standard likelihood procedures, developed for inference about fixed unknown parameters, can be used for inference about random effects. We show that the necessary standard error for the prediction interval of the random effect can be computed from the Hessian matrix of the h-likelihood. We also show numerically that the h-likelihood provides a prediction interval that maintains a more precise coverage probability than the BLUP method.     

配额制对近期国内电影市场自给率的影响

此项研究主要考察电影配额制及其它相关因素对电影市场自给率的影响。回归模型表明，配额制与自给率正相关的假设并不成立，因而暗示了配额制或许并不能有效的限制国外电影进入本国市场。国内生产总值，票房收益和制作投资被认为是决定自给率的最强有力的三大因素，而文化折扣和英语语言是非决定性因素。     

THE BASIC SKILLS EVALUATION DEVICE

The Commission on Accreditation for Marriage and Family Therapy Education (COAMFTE) requires that accredited programs evaluate trainees' clinical skills at various times during trainees' programs. The Commission does not attempt, however, to describe for programs eigher the nature of the skills nor how they are to be evaluated, leaving this to the programs to create. This paper describes the development and uses of the Basic Skills Evaluation Device (BSED). Using a published list of skills (Figley & Nelson, 1989), data from the literature, and data collected from COAMFTE accredited and candidacy programs, the authors and their colleagues developed a device for supervisors to use in evaluating beginning family therapists. Data regarding the reliability of the device presented, along with limitations and suggestions for various ways of using the device.     

Japanese and American Children's Reasoning about Accepting Credit for Prosocial Behavior

Children's reasoning about the appropriateness of accepting credit for one's own prosocial behavior was examined. Participants aged 7–11 years old in Japan and the USA (total N = 206) were presented with a series of stories in which a protagonist performs a good deed and is asked about it by another character. Across stories, the protagonist either truthfully acknowledges the deed or falsely denies it, in a statement that is made either in public or in private, and is addressed to either a teacher or to a peer. As predicted, Japanese children judged protagonists less favorably when they acknowledged the good deed in public rather than in private. Further, Japanese children tended to view modest lies more favorably overall than did children in the USA. These results point to the importance of modesty in Japan and to the ways in which Japanese children take into account the social context of communication when deciding whether it is appropriate for individuals to convey information about themselves.     

Key personality traits of engineers for innovation and technology development

Focusing on new roles of engineers for technological innovation and internal entrepreneurship, we examined the personality traits of 4876 engineers versus 75,892 non-engineers. Engineers scored higher on Tough-Mindedness and Intrinsic Motivation; but lower on Assertiveness, Conscientiousness, Customer Service Orientation, Emotional Stability, Extraversion, Image Management, Optimism, Visionary Style, and Work Drive. All but four of these traits were positively related to engineers’ career satisfaction. Overall, the results are not encouraging for the new roles of engineers such as intrapreneurship. Findings were discussed in terms of occupational profiling of engineers as well as career planning, selection, training, and professional development of engineers.     

Dimensions and design criteria for developing training reaction evaluations

Although there is research on training program evaluation, there is little systematic research on the design, development and use of training reaction evaluations. In order to obtain meaningful information from a program evaluation, evaluation professionals must be rigorous in the design and development of all aspects of an evaluation study, including instrumentation. The purposes of the study were to classify the dimensions of information sought using reaction evaluations and to establish design criteria for developing training reaction instruments. There were three major phases of the study: (1) classification of the dimensions and questionnaire design criteria used in reaction evaluations; (2) validation of the classified dimensions and the questionnaire design criteria by subject matter experts; and (3) assessment of a sample of training reaction instruments currently used in training programs in US corporations. The research findings were: eleven dimensions for reaction evaluation were identified and classified by purpose. Five overall design criteria, each consisting of several sub-criteria, were judged important in the design of reactionnaires. These include: introduction and directions; question format; question construction; questionnaire layout; and data analysis. It was concluded that a well-designed training reaction instrument integrates the proper application of design criteria with appropriate reaction dimensions. Most training reaction instruments used by US corporations consisted of questions representing only a few dimensions. The instruments varied in form and length. Few of them properly utilized the established questionnaire design criteria.