A new model selection procedure based on dynamic quantile regression

In this article, we propose a novel robust data-analytic procedure, dynamic quantile regression (DQR), for model selection. It is robust in the sense that it can simultaneously estimate the coefficients and the distribution of errors over a large collection of error distributions even those that are heavy-tailed and may not even possess variances or means; and DQR is easy to implement in the sense that it does not need to decide in advance which quantile(s) should be gathered. Asymptotic properties of related estimators are derived. Simulations and illustrative real examples are also given.     

Some notes on robust sure independence screening

Sure independence screening (SIS) proposed by Fan and Lv [4 J. Fan and R. Li, Variable selection via nonconcave penalized likelihood and its oracle properties, J. Amer. Statist. Assoc. 96 (2001), pp. 1348–1360. doi: 10.1198/016214501753382273[Taylor &; Francis Online], [Web of Science ®] , [Google Scholar]] uses marginal correlations to select important variables, and has proven to be an efficient method for ultrahigh-dimensional linear models. This paper provides two robust versions of SIS against outliers. The two methods, respectively, replace the sample correlation in SIS with two robust measures, and screen variables by ranking them. Like SIS, the proposed methods are simple and fast. In addition, they are highly robust against a substantial fraction of outliers in the data. These features make them applicable to large datasets which may contain outliers. Simulation results are presented to show their effectiveness.     

Supplier Evaluation and Selection Based on Stochastic Dominance: A Quality-Based Approach

Quality has become a major business strategy such that organizations with successful improvement of their products quality can gain productivity, enhance market penetration, achieve great profitability, and strongly sustain their competitive advantages. The quality of materials received from suppliers determines not only the quality of assembled products but also satisfaction and loyalty of downstream customers. In this article, we employ decision-making processes of the stochastic dominance on the basis of loss-based capability indices to compare certain potential suppliers. In view of compared results of the first-order and second-order stochastic dominances, each supplier is categorized as a superior supplier, weakly superior supplier, strongly non dominated supplier, or non dominated supplier. We develop a general computational procedure to select the preferable suppliers in an analytical way. To assist decision-makers in selecting preferable suppliers, quantile-quantile plots of loss-based capability indices presenting the results of the first-order stochastic dominance of the indices’ estimators are developed so that they can simultaneously visualize pair-wise comparisons of the suppliers and make appropriate decisions. Finally, a practical example invoking the stochastic dominance using the loss-based capability indices to carry out the quality-based supplier evaluation and selection is presented to demonstrate the applicability of our proposed methodology.     

Adaptive Percolation Using Subjective Likelihoods

A phenomenon that I call “adaptive percolation” commonly arises in biology, business, economics, defense, finance, manufacturing, and the social sciences. Here one wishes to select a handful of entities from a large pool of entities via a process of screening through a hierarchy of sieves. The process is not unlike the percolation of a liquid through a porous medium. The probability model developed here is based on a nested and adaptive Bayesian approach that results in the product of beta-binomial distributions with common parameters. The common parameters happen to be the observed data. I call this the percolated beta-binomial distribution . The model turns out to be a slight generalization of the probabilistic model used in percolation theory. The generalization is a consequence of using a subjectively specified likelihood function to construct a probability model. The notion of using likelihoods for constructing probability models is not a part of the conventional toolkit of applied probabilists. To the best of my knowledge, a use of the product of beta-binomial distributions as a probability model for Bernoulli trials appears to be new. The development of the material of this article is illustrated via data from the 2009 astronaut selection program, which motivated this work.     

矩约束模型的最优矩条件选取方法

大量经济、金融以及企业管理等领域研究对象的行为特征可以通过矩约束模型来刻画。然而,该模型中参数的估计对矩条件的选取非常敏感。如何选取最优的矩条件,进而得到更准确的参数估计和更精确的统计推断,是实证研究面临的重要问题。本文从估计量均方误差（MSE）最小的角度,研究了一般矩约束模型两步有效广义矩（GMM）估计的最优矩条件选取方法。首先,利用迭代的方法,推导出两步有效GMM估计的高阶MSE,然后通过Nagar分解,求出了两步有效GMM估计量的近似MSE。接着,基于近似MSE表达式,给出了两步有效GMM估计矩条件选取准则的一般理论,即定义了最优的矩条件,提出了两步有效GMM估计的最优矩条件选取准则,并证明了选取准则的渐近有效性。模拟结果表明,本文提出的矩条件选取方法能够很好地改善两步有效GMM估计量的有限样本表现,降低估计量的有效样本偏差。本研究为实证研究中面临的矩条件选择问题提供了理论依据。     

Cycles of Adaptive Strategies Over the Life Course

An increasing number of Australia’s ageing population are aging with long-term physical impairments. This study explored the life experiences of this group using a qualitative approach. In-depth interviews were conducted with 10 disabled Victorians, aged between 51 and 84 years, and an inductive thematic analysis undertaken. A relationship was found between the adaptive strategies that participants developed as they moved through life phases and the impairment stages. The implications of the emergence of a cyclical process of adaptation across the life course. and particularly in respect of aging, delivery of aged-care services and social workers in this sector are discussed.     

Toleration or trust? Investigating the acceptance of ‘boat people’ among young Australians

There has been intense debate in Australia regarding how asylum seekers who arrive by boat should be treated. Some call for compassion towards those prepared to risk their lives to seek protection, whereas others believe ‘boat people’ should not be allowed into the country. This article uses data from a large representative sample of young people in Queensland, Australia, to understand the acceptance of asylum seekers by young people in Australia. The findings suggest that young Australians are more accepting than the Australian adult population. Several social and political background factors were also found to be associated with the belief that ‘boat people’ should be permitted into Australia. Fewer factors, however, are associated with the trust young Australians have in people from another country. This suggests that while some young Australians may believe boats carrying asylum seekers should not be turned away, fewer might be prepared to enter into trusting relationships with ‘boat people’ should they resettle in Australia.     

Variable selection for multivariate generalized linear models

Generalized linear models (GLMs) are widely studied to deal with complex response variables. For the analysis of categorical dependent variables with more than two response categories, multivariate GLMs are presented to build the relationship between this polytomous response and a set of regressors. Traditional variable selection approaches have been proposed for the multivariate GLM with a canonical link function when the number of parameters is fixed in the literature. However, in many model selection problems, the number of parameters may be large and grow with the sample size. In this paper, we present a new selection criterion to the model with a diverging number of parameters. Under suitable conditions, the criterion is shown to be model selection consistent. A simulation study and a real data analysis are conducted to support theoretical findings.     

Variable selection in the high-dimensional continuous generalized linear model with current status data

In survival studies, current status data are frequently encountered when some individuals in a study are not successively observed. This paper considers the problem of simultaneous variable selection and parameter estimation in the high-dimensional continuous generalized linear model with current status data. We apply the penalized likelihood procedure with the smoothly clipped absolute deviation penalty to select significant variables and estimate the corresponding regression coefficients. With a proper choice of tuning parameters, the resulting estimator is shown to be a root n/p_n-consistent estimator under some mild conditions. In addition, we show that the resulting estimator has the same asymptotic distribution as the estimator obtained when the true model is known. The finite sample behavior of the proposed estimator is evaluated through simulation studies and a real example.     

作业成本动因选择、合并与评价的系统方法构建

目前学术界关于作业成本动因选择与合并的研究,缺乏对动因留选与留选个数的探讨,而关于对成本动因选择合并的评价的研究未见。可以通过聚类分析建立模型,得到成本动因的相关类,再结合主成分分析指导留选动因的个数,最终确定留选动因,并首次建立评价动因选择与合并优劣性的主成分分析模型。实证分析表明,此系统方法更好地解决了成本动因选择与合并的问题,相同数据下该方法比矩阵理论与距离聚类分析结果更优,作业成本管理系统的复杂性与信息成本显著降低。本文为作业成本动因的选择与合并以及评价提供了一套系统方法。