Nonparametric Bayes methods for directional data

A model for directional data in q dimensions is studied. The data are assumed to arise from a distribution with a density on a sphere of q — 1 dimensions. The density is unimodal and rotationally symmetric, but otherwise of unknown form. The posterior distribution of the unknown mode (mean direction) is derived, and small-sample posterior inference is discussed. The posterior mean of the density is also given. A numerical method for evaluating posterior quantities based on sampling a Markov chain is introduced. This method is generally applicable to problems involving unknown monotone functions.     

Comparing confidence intervals for the logarithmic series distribution

It is assumed that a small random sample of fixed size n is drawn from a logarithmic series distribution with parameter θ and that it is desired to estimate θ by means of a two-sided confidence interval. In this note Crow's system of confidence intervals is compared, in shortness of intervals, with Clopper and Pearson's, and the corresponding randomized counterparts.     

Quality of Work Life and Turnover Intention: A Partial Least Square (PLS) Approach

The purpose of this study is to model the relationship of quality of work life factors and turnover intention among accounting professionals in Malaysia. Data was collected using a structured questionnaire gleaned from the literature. The data was analyzed using Smart Partial Least Squares a second generation structural equation modeling software. The results indicate that supervisory behavior, job characteristics and work life balance all have a significant negative relationship with turnover intention with work life balance the most significant predictor of turnover intention. Implications from this research is further explored.     

The Retrenchment of the Welfare State in Latin America: The Case of Argentina

According to the conventional approving account of the transformations which have been taking place in public policy and in markets in Latin America, Argentina constitutes one of the most successful examples of wide-ranging and rapid change. Certainly the experience of Argentina offers an excellent case-study of what in the literature is termed " the retrenchment of the welfare states"; that is those institutional transformations associated with the "neoconservative revolutions" of recent years. In this paper I analyse the characteristics of Argentinian welfare state retrenchment, distinguishing between two fields of analysis: (1) "systemic retrenchment" which is linked to changes in the "referential environment" of social policy institutions, especially changes in the economic, fiscal, labour market and politico-institutional contexts: (2) "programmatic retrenchment" which refers to changes in the institutional ordering of specific social policies. Finally I draw conclusions in respect of the strategies adopted for the retrenchment of the welfare state in Argentina and discuss probable prospects for the future.     

Assisting ex-offenders in employment: the experience of Hong Kong

Research indicates that employment is effective in reducing recidivism amongst ex-offenders. However, ex-offenders are also discouraged from obtaining employment as a result of their poor education level, deficits in vocational skills and employer bias and discrimination. In Hong Kong, the Society of Rehabilitation and Crime Prevention offers a wide range of services to assist ex-offenders in employment. While a number of ex-offenders have benefited from these services, continuing difficulties are hard to overcome without government support. This paper recommends a multi-disciplinary approach to improve the employment situation of ex-offenders in Hong Kong and advocates for greater government involvement to help facilitate the reintegration of ex-offenders into the community in Hong Kong.     

Optimal robust parameter designs with qualitative and quantitative factors

Robust parameter design is an effective methodology for reducing variance and improving the quality of a product and a process. Recent work has mainly concentrated on two‐level robust parameter designs. We consider general robust parameter designs with factors having two or more or mixed levels these levels being either qualitative or quantitative. We propose a methodology and develop a generalised minimum aberration optimality criterion for selecting optimal robust parameter designs. A catalogue of 18‐run optimal designs is constructed and tabulated.