Simultaneous prediction intervals for all patrwise differences among several future sample means

Hahn (1977) suggested a procedure for constructing prediction intervals for the difference between the means of two future samples from normal populations having equal variance, based on past samples selected from both populations. In this paper, we extend Hahn's work by constructing simultaneous prediction intervals for all pairwise differences among the means of k ≥ 2 future samples from normal populations with equal variances, using past samples taken from each of the k populations. For K = 2, this generalization reduces to Hahn's special case. These prediction intervals may be used when one has sampled the performance of several products and wishes to simultaneously as- sess the differences in future sample mean performance of these products with a predetermined overall coverage probability. The use of the new procedure is demonstrated with a numerical example.     

Comparisons of Software Packages for Generalized Linear Multilevel Models

We review five software packages that can fit a generalized linear mixed model for data with more than a two-level structure and a multiple number of independent variables. These five packages are MLn, MLwiN, SAS Proc Mixed (Glimmix Macro), HLM, and VARCL. We first discuss the features of each of the five packages. These features include data input and data management, statistical model capabilities, output, and user friendliness. We then compare their performance on several simulated datasets.     

A generalized drop-the-loser rule for multi-treatment clinical trials

Urn models are popular for response adaptive designs in clinical studies. Among different urn models, Ivanova's drop-the-loser rule is capable of producing superior adaptive treatment allocation schemes. Ivanova [2003. A play-the-winner-type urn model with reduced variability. Metrika 58, 1–13] obtained the asymptotic normality only for two treatments. Recently, Zhang et al. [2007. Generalized drop-the-loser urn for clinical trials with delayed responses. Statist. Sinica, in press] extended the drop-the-loser rule to tackle more general circumstances. However, their discussion is also limited to only two treatments. In this paper, the drop-the-loser rule is generalized to multi-treatment clinical trials, and delayed responses are allowed. Moreover, the rule can be used to target any desired pre-specified allocation proportion. Asymptotic properties, including strong consistency and asymptotic normality, are also established for general multi-treatment cases.     

Successful entrepreneurship in Hong Kong

The business performance of Chinese firms throughout the world is generally regarded as outstanding. It is also generally accepted in the literature that entrepreneurial business firms play a significant role in economic development of countries at every level of industrialization. Even though entrepreneurship is a major influencing factor for economic growth and development, the interpretation of this factor is still debatable. This paper examines the following factors which might influence the emergence of entrepreneuship: (1) economic; (2) non-economic; and (3) psychological. It then relates these factors to Chinese culture in an attempt to explain the apparent outstanding entrepreneurial skills of the Chinese people. As for economic factors, in Hong Kong the free open market and voluntary exchange provide freedom for distribution of income which in turn allows business practitioners to retain profits and accumulate wealth. Non-economic factors in Hong Kong include is blocked upward mobility in political channels in the colonial environment. This causes the Chinese to use economic mobility as an alternative. Psychological factors include the viewpoint that Chinese are more concerned about a sense of personal or individual achievement, power and influence than other cultures. This causes the Hong Kong Chinese to shift their achievement drives to business success and this encourages entrepreneurship.     

Come one, come all

Aging is a complex process that involves the gradual functional decline of many different tissues and cells. Gene expression microarray analysis provides a comprehensive view of the gene expression signature associated with age and is particularly valuable for understanding the molecular mechanisms that contribute to the aging process. However, because of the stochastic nature of the aging process, animals of the same chronological age often manifest great physiological differences. Therefore, profiling the gene expression pattern of a large population of aging animals risks either exaggerating or masking the changes in gene expression that correspond to physiological aging. In a recent paper, Golden and Melov surveyed the gene expression profiles of individual aging Caenorhabditis elegans, hoping to circumvent the problem of variability among worms of the same chronological age. This initial analysis of age-dependent gene expression in individual aging worms is an important step toward deciphering the molecular basis of physiological aging.     

A Note on the Modified Likelihood Ratio Test for Homogeneity in Beta Mixture Models

This article presents a note on the modified likelihood ratio test for homogeneity in beta mixture models. Under consistency of the penalized maximum likelihood estimators, the limiting distribution of the test statistic converges to the chi-bar-squared distributions. The statistic degenerates to zero with a weight due to the negative definiteness of a complicated random matrix. The probability that this matrix is negative definite is related to the parameter values under the homogeneity hypothesis. The dependency pattern enables the introduction of an upper bound on the asymptotic null distribution. Simulation study is investigated to verify the accuracy of the results.     

Assessing readiness to work from a stages of change perspective: implications for return to work

The Lam Assessment on Stages of Employment Readiness (LASER) was developed to assess welfare recipients' employment readiness. The LASER consists of 14 items corresponding to Prochaska's stages of change model (Prochaska, DiClemente and Norcross, 1992). A sample of 149 welfare recipients from a work training program participated in the study. The Confirmatory Factor Analysis (CFA) supported the three factors structure corresponding to Prochaska's Pre-Contemplation, Contemplation, and Action stages. A cluster analysis classified the sample into three groups according to their LASER scores. A six months follow-up on employment outcomes showed that those who were in Pre-contemplation stage had the poorest employment outcome (25%), those who were in the Action stage had the best outcome (56%) and those in the Contemplation stage were in between (38%). Implications for work rehabilitation and treatment matching were discussed.     

Vestiges of the medical model: a critical exploration of the Ontario Disability Support Program in Ontario,Canada

Although ample literature exists on workfare in Ontario, Canada, research on the social assistance programme for disabled people, the Ontario Disability Support Program (ODSP), is relatively scant. What we do know points to similar shortcomings. We present a critical disability study considering four policy domains to explore how disabled people are identified and accommodated in Ontario. Discussing the principles of universal design, we argue for policy design that meets the needs of as many individuals as possible, while accounting for significant human variability. We conclude that the ODSP, in failing to adopt a rights-based framework, violates the dignity and rights of disabled people.