Shrinkage inverse regression estimation for model-free variable selection

Summary.  The family of inverse regression estimators that was recently proposed by Cook and Ni has proven effective in dimension reduction by transforming the high dimensional predictor vector to its low dimensional projections. We propose a general shrinkage estimation strategy for the entire inverse regression estimation family that is capable of simultaneous dimension reduction and variable selection. We demonstrate that the new estimators achieve consistency in variable selection without requiring any traditional model, meanwhile retaining the root n estimation consistency of the dimension reduction basis. We also show the effectiveness of the new estimators through both simulation and real data analysis.     

博彩者特征和彩票功能悖论

一些经济学理论认为理性的人可能在一定情形下因偏好风险而参加博彩,而一些心理学实验研究则发现博彩者可能存在系统性的心理偏误。对理论的分析发现,彩票对穷人更具有吸引力且博彩者存在非理性心理。国内实证文献也支持这两个结论。如果博彩行为是非理性行为,那么博彩业就有利用人们非理性幼稚心理牟利的嫌疑。政府宣称发行彩票的目的是筹集资金用于社会公益事业,这就形成了一个悖论,即从贫穷群体那里筹集资金来改善他们的处境。     

Conditional variance estimation in heteroscedastic regression models

First, we propose a new method for estimating the conditional variance in heteroscedasticity regression models. For heavy tailed innovations, this method is in general more efficient than either of the local linear and local likelihood estimators. Secondly, we apply a variance reduction technique to improve the inference for the conditional variance. The proposed methods are investigated through their asymptotic distributions and numerical performances.     

A new estimation method for Weibull-type tails based on the mean excess function

Studying the right tail of a distribution, one can classify the distributions into three classes based on the extreme value index γ$\gamma$. The class γ>0$\gamma >0$ corresponds to Pareto-type or heavy tailed distributions, while γ<0$\gamma <0$ indicates that the underlying distribution has a finite endpoint. The Weibull-type distributions form an important subgroup within the Gumbel class with γ=0$\gamma =0$. The tail behaviour can then be specified using the Weibull tail index. Classical estimators of this index show severe bias. In this paper we present a new estimation approach based on the mean excess function, which exhibits improved bias and mean squared error. The asserted properties are supported by simulation experiments and asymptotic results. Illustrations with real life data sets are provided.     

Measuring the health patterns of the ‘mixed/multiple’ ethnic group in Britain: data quality problems,reporting issues,and implications for policy

The ‘mixed’ group, officially recognised in the 2001 Census, is one of the most rapidly growing ethnic groups in Britain. Although ‘mixed’ categorisation was added to ethnic coding in NHS datasets, our knowledge of health patterns for this population is meagre. Data quality problems remain a key obstacle, including poor reproducibility of the data and constraints on reporting due to sparse data bias. The consequent minimal and indicative evidence base has focused mainly on risky health behaviours, mental health and generic measures of self-rated health, as it has in the U.S.A. and Canada. There is negligible information on the main underlying causes of death, such as neoplasms, heart disease and stroke. Consideration should be given to pooling data across multiple years of health and general purpose surveys to enable reporting for the four ‘mixed’ categories and adjustment for mediating factors and relevant confounders, such as measures of socio-economic status.     

Estimates of subgroup treatment effects in overall nonsignificant trials: To what extent should we believe in them?

In drug development, it sometimes occurs that a new drug does not demonstrate effectiveness for the full study population but appears to be beneficial in a relevant subgroup. In case the subgroup of interest was not part of a confirmatory testing strategy, the inflation of the overall type I error is substantial and therefore such a subgroup analysis finding can only be seen as exploratory at best. To support such exploratory findings, an appropriate replication of the subgroup finding should be undertaken in a new trial. We should, however, be reasonably confident in the observed treatment effect size to be able to use this estimate in a replication trial in the subpopulation of interest. We were therefore interested in evaluating the bias of the estimate of the subgroup treatment effect, after selection based on significance for the subgroup in an overall “failed” trial. Different scenarios, involving continuous as well as dichotomous outcomes, were investigated via simulation studies. It is shown that the bias associated with subgroup findings in overall nonsignificant clinical trials is on average large and varies substantially across plausible scenarios. This renders the subgroup treatment estimate from the original trial of limited value to design the replication trial. An empirical Bayesian shrinkage method is suggested to minimize this overestimation. The proposed estimator appears to offer either a good or a conservative correction to the observed subgroup treatment effect hence provides a more reliable subgroup treatment effect estimate for adequate planning of future studies.     

Vine copula constructions of higher-dimensional dependent reliability systems

Copulas have proved to be very successful tools for the flexible modeling of dependence. Bivariate copulas have been deeply researched in recent years, while building higher-dimensional copulas is still recognized to be a difficult task. In this paper, we study the higher-dimensional dependent reliability systems using a type of decomposition called “vine,” by which a multivariate distribution can be decomposed into a cascade of bivariate copulas. Some equations of system reliability for parallel, series, and k-out-of-n systems are obtained and then decomposed based on C-vine and D-vine copulas. Finally, a shutdown system is considered to illustrate the results obtained in the paper.     

The role of social and cognitive factors in individual gambling: An empirical study on college students

Most of the studies on the determinants of individual gambling behaviour rely on cognitive theories. In our study, we argue that, besides cognitive factors, several social factors might play an important role as well. We analyse data from an ad hoc webmail survey conducted on about 2000 undergraduate students enrolled in a large public university in the Northern Italy in the academic year 2012–13. Using a variety of statistical techniques (standard regression models, boosted regression trees and structural equations models), we show that social variables affect both participation in gambling in the past year and latent gambling propensity. In particular, controlling for several proxies for individual cognitive ability and understanding of probability, gambling propensity is positively affected by the degree of gambling in the social surrounding (parents, peers, neighbourhood) and the acceptability of gambling activities to the individual. Moreover, in our sample of college students the role of social factors appears to be larger than that of cognitive factors, and this is consistent across different types of models and specifications.     

Inappropriate Comparisons: The LGB Population's Missing Reference Group

ABSTRACT

Given that many professional organizations emphasize the need for comparing assessment results to appropriate reference groups in their codes of ethics, we consider this practice through an ecological perspective as it applies to the lesbian, gay, and bisexual (LGB) population. The purpose of norming and types of assessment bias is discussed with respect to LGB population, which frequently lack specific norming data. The authors discuss whether the LGB population has characteristics similar to other commonly normed for groups and explore how group-shared constructs such as minority stress and internalized homophobia may introduce bias and affect the validity of assessments. A social anxiety assessment as well as a personality disorder inventory are examined for bias as case examples explaining how these assessments may exhibit bias when used with the LGB population. Increases in validity and effects on treatment planning are discussed as benefits of providing LGB-specific norms. Risks of providing these norms, such as minimizing subgroup differences and possibly increasing the risk of discrimination are also addressed before providing clinicians with recommendations as to how they may minimize the risk of bias in their assessment process.