Another look at Huber's estimator: A new minimax estimator in regression with stochastically bounded noise

Huber's estimator has had a long lasting impact, particularly on robust statistics. It is well known that under certain conditions, Huber's estimator is asymptotically minimax. A moderate generalization in rederiving Huber's estimator shows that Huber's estimator is not the only choice. We develop an alternative asymptotic minimax estimator and name it regression with stochastically bounded noise (RSBN). Simulations demonstrate that RSBN is slightly better in performance, although it is unclear how to justify such an improvement theoretically. We propose two numerical solutions: an iterative numerical solution, which is extremely easy to implement and is based on the proximal point method; and a solution by applying state-of-the-art nonlinear optimization software packages, e.g., SNOPT. Contribution: the generalization of the variational approach is interesting and should be useful in deriving other asymptotic minimax estimators in other problems.     

Regularization through variable selection and conditional MLE with application to classification in high dimensions

It is often the case that high-dimensional data consist of only a few informative components. Standard statistical modeling and estimation in such a situation is prone to inaccuracies due to overfitting, unless regularization methods are practiced. In the context of classification, we propose a class of regularization methods through shrinkage estimators. The shrinkage is based on variable selection coupled with conditional maximum likelihood. Using Stein's unbiased estimator of the risk, we derive an estimator for the optimal shrinkage method within a certain class. A comparison of the optimal shrinkage methods in a classification context, with the optimal shrinkage method when estimating a mean vector under a squared loss, is given. The latter problem is extensively studied, but it seems that the results of those studies are not completely relevant for classification. We demonstrate and examine our method on simulated data and compare it to feature annealed independence rule and Fisher's rule.     

一种新的右手定则替代佛莱铭左手及右手定则

大凡读过高中的人,都知道佛莱铭左手和右手定则,这种左、右定则很容易记错,有时要将手扭歪才能判定其方向,很难运用．为了方便学生记忆及方便判定方向,设法设计出一种新的右手定则,可以同时判定磁场对电流的作用力及磁场中导线所产生的感生电流的方向,显然这种右手定则是一个创新．     

Are Father’s or Mother’s Socioeconomic Characteristics More Important Influences on Student Performance? Recent International Evidence

Since the early 1970s the importance of mothers’ socioeconomic characteristics on their children’s educational and occupational attainment has been acknowledged. However, it is not clear if fathers’ characteristics have a stronger influence because men usually have stronger attachments to the labour market, or alternatively mothers’ characteristics are more important because of their greater role in children’s socialization. This study addresses this question by comparing the influence of father’s and mother’s education and occupation on student performance in literacy and numeracy using data from 30 countries. The impact of mother’s education is usually greater or comparable to that of father’s education. In contrast, substantially stronger effects for mother’s occupational status compared to father’s were rare. In most countries the impact of mother’s socioeconomic characteristics (education plus occupation) on student performance is comparable to that for father’s. Of the four indicators of socioeconomic background, father’s occupational status and mother’s educational attainment tend to have stronger effects, although many countries do not conform to this pattern. There are indications that the relative importance of mother’s characteristics have increased over time.

Inference in a Binary Response Model with Applications to Data Analysis*

Standard errors of the coefficients of a logistic regression (a binary response model) based on the asymptotic formula are compared to those obtained from the bootstrap through Monte Carlo simulations. The computer intensive bootstrap method, a nonparametric alternative to the asymptotic estimate, overestimates the true value of the standard errors while the asymptotic formula underestimates it. However, for small samples the bootstrap estimates are substantially closer to the true value than their counterpart derived from the asymptotic formula. The methodology is discussed using two illustrative data sets. The first example deals with a logistic model explaining the log-odds of passing the ERA amendment by the 1982 deadline as a function of percent of women legislators and the percent vote for Reagan. In the second example, the probability that an ingot is ready to roll is modelled using heating time and soaking time as explanatory variables. The results agree with those obtained from the simulations. The value of the study to better decision making through accurate statistical inference is discussed.     

Prevalence,people and processes: a consideration of the implications of Lord Laming's progress report on the protection of children in England

Media coverage of the death of Baby P revived national concerns about the standard of child safeguarding practice in England following the implementation of widespread structural changes in response to the Victoria Climbié Inquiry chaired by Lord Laming in 2003. This paper discusses the recommendations of Lord Laming's recent Progress Report. It questions whether the scale of the challenge in improving child protection is fully recognised and considers briefly the culture of social care in the UK and the barriers to effective reform. Copyright © 2009 John Wiley & Sons, Ltd.     

Children’s Psychosocial Rehabilitation: Clinical Outcomes for Youth with Serious Emotional Disturbance Living in Foster Care

Children living in foster care are an especially vulnerable population who often come to the attention of Medicaid mental health providers. These children experience a high incidence of emotional and behavioral disorders and may have specialized treatment needs related to their living arrangement status. This study assessed whether Children’s Psychosocial Rehabilitation could effectively treat youth with severe emotional and behavioral disorders who live in foster care. Analysis of data from an open trial of 218 clinically-impaired youth, aged 3–18 years, revealed no reliable differences in treatment outcome between foster versus non-foster children, with a trend toward more favorable outcomes for foster youth. Findings justify further study of the effectiveness of this Medicaid-funded service for the treatment of youth in care.     

Getting to know reality and breaking stereotypes: the experience of two generations of working disabled women

This paper sets out the results of a Spanish study of the experience and meaning of work among disabled women of two generations, with three types of disability (physical, visual and hearing). Performing a socially recognised activity such as a job is a source of emotional welfare and self‐esteem. Moreover, it confers a certain social status. For the participants in this study the kind of work involved, whether productive, paid and ‘extra‐domestic’ or ‘reproductive’, unpaid and done at home, acquires different meanings, since for disabled women, sexist stereotypes – already more or less accentuated in the culture – social attitudes towards disability and personal factors introduce relevant differences, while leading to conflicts and dilemmas that these women have to solve. At any rate, their sense of responsibility in performing all types of work should be emphasised as evidence of their sense of independence and personal competence, forming a keystone in their construction of a sense of identity and social integration.     

The impact of migration on the well-being of transnational families: new data from sending communities in Mexico

We present results from a new study of the effects of migration to the USA on the well-being of transnational families in high emigration communities within Mexico. Our survey measured the well-being of family members in a variety of domains: economic, health, education, and child development for a representative sample drawn from high migration municipalities. Compared to those with no recent emigrants to the USA, Mexican households sending non-caregivers to the USA appear to gain economically without contributing to problems faced by children. However, when family caregivers migrate to the USA, the remaining members in Mexico struggle to meet the family's needs and children are more vulnerable to educational, emotional, and health problems. Children in households where a caregiver migrated were more likely to have frequent illnesses (10% vs. 3%, p<0.0001), chronic illness (7% vs. 3%, p=0.011), emotional problems (10% vs. 4%, p=0.006), and behavioral problems (17% vs. 10%, p=0.018) compared with children in households where the migrant was not a caregiver. Research, policy, and program implications of these findings are discussed.     

Transfer Pricing in Transition Economies: Evidence from Ukraine

Faced with possibilities and challenges of doing business under different regulatory regimes, transnational corporations have developed a number of transfer mechanisms to take advantage of profit maximization opportunities. Transfer pricing is a transfer mechanism widely used by transnational corporations. Implications of transfer pricing for profitability and the need for transfer pricing regulation are well understood by national governments, which is reflected in the fact that more than 60 governments have introduced some form of transfer pricing controls. Transfer pricing is a challenging issue for transition economies as their transfer pricing regulatory systems are less mature than those of developed countries. The authors have initiated an empirical study on transfer pricing strategies in the Ukrainian market. In addition, the national regulatory regime for transfer pricing was evaluated compared to international best practices. This article is an attempt to draw attention of the research community and Ukrainian policy-makers to transfer pricing issues in Ukraine.