Simulation from a Target Distribution Based on Discretization and Weighting

We present a simulation method which is based on discretization of the state space of the target distribution (or some of its components) followed by proper weighting of the simulated output. The method can be used in order to simplify certain Monte Carlo and Markov chain Monte Carlo algorithms. Its main advantage is that the autocorrelations of the weighted output almost vanish and therefore standard methods for iid samples can be used for estimating the Monte Carlo standard errors. We illustrate the method via toy examples as well as the well-known dugongs and Challenger datasets.     

Under Fives: Thirty Years of No Progress?

SUMMARY. The value of preschool education was already well recognised 30 years ago but the UK, unlike other European countries, has never developed a coherent system of public provision for young children. Reliance on private, voluntary and self-help facilities to fill the gaps has produced diversity but variable quality and little real choice. Over the same period attitudes and family structures have changed and there have been great advances in our understanding of how children's development can be supported and enhanced. The Children Act 1989 provides a legal framework for translating this knowledge into action. Yet at a time when a remarkable degree of professional consensus has been achieved on what is needed, we seem as far as ever from an adequate level of good quality provision. The article suggests that the reason is to be found in the marginalisation of our youngest children as the concern only of their parents and not of society as a whole.     

On the explosion rate of maximum-bias functions

The maxbias function B_T() contains much information about the robustness properties of the estimate T. This function satisfies B_T(0)=0 and B_T()<for all 0<<whereis the breakdown point of T. Hampel (1974)pioneered the study of the limiting behaviour of B_T(?) where ? → 0. He computed and optimized the rate γ at which B_T(?) approaches 0 when ? → 0. This rate is now called the contamination sensitivity of T, and constitutes one of the cornerstones of the theory of robustness. We show that much can also be learned from the study of the limiting behaviour of B_T(?) when ? → ?*. A new robustness measure, called the relative explosion rate, can be obtained by studying the limiting relative maxbias behaviour of two extimates when approaches their common breakdown point ?*. Like the contamination sensitivity, the relative explosion rate can be readily derived from the estimate's score function. General formulae are given for M-estimates of scale and S-, MM- and τ-estimates of regression. We also show that the maxbias behaviour for large ? is largely determined by the curvature of the estimate's score function near zero. This motivates our definition and study of the local order of a score function.     

Two-stage time minimizing assignment problem

This paper deals with the optimal selection of m out of n facilities to first perform m   given primary jobs in Stage-I followed by the remaining (n-m)$(n-m)$ facilities performing optimally the (n-m)$(n-m)$ secondary jobs in Stage-II. It is assumed that in both the stages facilities perform in parallel. The aim of the proposed study is to find that set of m   facilities performing the primary jobs in Stage-I for which the sum of the overall completion times of jobs in Stage-I and the corresponding optimal completion time of the secondary jobs in Stage-II by the remaining (n-m)$(n-m)$ facilities is the minimum. The developed solution methodology involves solving the standard time minimizing and cost minimizing assignment problems alternately after forbidding some facility-job pairings and suggests a polynomially bound algorithm. This proposed algorithm has been implemented and tested on a variety of test problems and its performance is found to be quite satisfactory.     

A Predictive Study of Dirichlet Process Mixture Models for Curve Fitting

This paper examines the use of Dirichlet process mixtures for curve fitting. An important modelling aspect in this setting is the choice between constant and covariate‐dependent weights. By examining the problem of curve fitting from a predictive perspective, we show the advantages of using covariate‐dependent weights. These advantages are a result of the incorporation of covariate proximity in the latent partition. However, closer examination of the partition yields further complications, which arise from the vast number of total partitions. To overcome this, we propose to modify the probability law of the random partition to strictly enforce the notion of covariate proximity, while still maintaining certain properties of the Dirichlet process. This allows the distribution of the partition to depend on the covariate in a simple manner and greatly reduces the total number of possible partitions, resulting in improved curve fitting and faster computations. Numerical illustrations are presented.     

A bayesian predictive approach to sequential search for an optimal dose: Parametric and nonparametric models

Summary This paper looks at a new approach to the problem of finding the maximal tolerated dose (or optimal dose, Eichhorn and Zacks, 1973) of certain drugs which in addition to their therapeutic effects have secondary harmful effects. The problem is investigated in a sequential setting from a Bayesian predictive approach. Search procedures are proposed for parametric and nonparametric models.     

Infantilization as elder mistreatment:evidence from five adult day centers

To prevent maltreatment, aging services must be age appropriate even as consumers suffer from physical and cognitive disabilities. In this paper, it is argued that exposing older persons to childoriented settings, activities and speech patterns in aging service environments represent a form of psychological mistreatment. Ethnographic evidence from 220 hours of field observations in five "social model" adult day centers revealed infantilization of service users in the form of confinement, baby-talk, nicknames, child-oriented decor, teacher-student learning format, reprimands, use of toys, as well as a loss of privacy regulation, autonomy, choice, and adult status. All centers exhibited some mistreatment, but severe examples were present in two of the five centers studied. Negative influences on behavior, well-being, self-identity, relationship formation, and social interaction were detected, which distinguished mistreatment from poor quality of care. Insider interviews (23) revealed resentment and adaptive strategies employed to distance themselves from infantilization.     

Play the white man: the social construction of fairness and competition in equal opportunity policies

This paper discusses the impact of equal opportunity projects on women's employment in two public sector organisations. It examines the limitations of the emerging liberal model and assesses the likely effectiveness of alternative approaches. An Affirmative Action Program in a North American university was examined five years after its initiation. Despite standardised procedures for access to jobs and systematic monitoring, there was very little change in the degree of occupational segregation between men and women. A women's committee project in a UK university examined the present situations of women staff, with the aim of producing a strategy for change which would benefit women currently employed. This resulted in the identification of training provision, flexible working arrangements and the restructuring of job requirements as the central aspects of an alternative approach to equal opportunity policy. It is argued that, particularly in a recessionary economic climate, policies requiring employers to rethink job requirements in ways that do not exclude competent women should provide a more effective challenge to occupational segregation than liberal policies which concentrate on assessing the ‘suitability’ of individual job applicants in terms of conventional criteria.