Outlier detection and robust variable selection via the penalized weighted LAD-LASSO method

This paper studies the outlier detection and robust variable selection problem in the linear regression model. The penalized weighted least absolute deviation (PWLAD) regression estimation method and the adaptive least absolute shrinkage and selection operator (LASSO) are combined to simultaneously achieve outlier detection, and robust variable selection. An iterative algorithm is proposed to solve the proposed optimization problem. Monte Carlo studies are evaluated the finite-sample performance of the proposed methods. The results indicate that the finite sample performance of the proposed methods performs better than that of the existing methods when there are leverage points or outliers in the response variable or explanatory variables. Finally, we apply the proposed methodology to analyze two real datasets.     

Semiparametric regression of clustered current status data

This paper discusses regression analysis of clustered current status data under semiparametric additive hazards models. In particular, we consider the situation when cluster sizes can be informative about correlated failure times from the same cluster. To address the problem, we present estimating equation-based estimation procedures and establish asymptotic properties of the resulting estimates. Finite sample performance of the proposed method is assessed through an extensive simulation study, which indicates the procedure works well. The method is applied to a motivating data set from a lung tumorigenicity study.     

Toward an integrated Bayesian network approach to measurement error detection and correction

In this article, the quality of data produced by national statistical institutes and by governmental institutions is considered. In particular, the problem of measurement error is analyzed and an integrated Bayesian network decision support system based on non-parametric Bayesian networks is proposed for its detection and correction. Non-parametric Bayesian networks are graphical models expressing dependence structure via bivariate copulas associated to the edges of the graph. The network structure and the misreport probability are estimated using a validation sample. The Bayesian network model is proposed to decide: (i) which records have to be corrected; (ii) the kind and amount of correction to be adopted. The proposed correction procedure is applied to the Banca d’Italia Survey on Household Income and Wealth and, specifically, the bond amounts are analyzed. Finally, the sensitivity of the conditional distribution of the true value random variable given the observed one to different evidence configurations is studied.     

An improved cluster two-stage randomized response model

In this paper, Abdelfatah and Mazloum's (2015) two-stage randomized response model is extended to unequal probability sampling and stratified unequal probability sampling, both with and without replacement. The extended models result in more efficient estimators than Lee et al.'s (2014) estimators of the proportion of the population having a sensitive attribute.     

MSE performance of the weighted average estimators consisting of shrinkage estimators when each individual regression coefficient is estimated

In this paper, we analytically derive the exact formula for the mean squared error (MSE) of two weighted average (WA) estimators for each individual regression coefficient. Further, we execute numerical evaluations to investigate small sample properties of the WA estimators, and compare the MSE performance of the WA estimators with the other shrinkage estimators and the usual OLS estimator. Our numerical results show that (1) the WA estimators have smaller MSE than the other shrinkage estimators and the OLS estimator over a wide region of parameter space; (2) the range where the relative MSE of the WA estimator is smaller than that of the OLS estimator gets narrower as the number of explanatory variables k increases.     

日内知情交易概率测度及事件影响研究

在EKOP模型测度PIN的基础上,通过建立时变交易到达率模型,滚动计算日内知情交易概率,并将PIN测度与事件研究相结合,对比了不同规模公司股票在事件日前后PIN的变化情况。实证结果表明我国股市存在信息泄露情况,尤其是小规模公司股票在公告日前一天知情交易明显增加;前一笔知情交易对当前非知情交易有削弱作用,但对当前知情交易有加强作用,可以进一步解释交易的集簇现象：日内PIN对信息的刻画更加准确,但也发现在公共事件发生后第二天PIN仍会增加,这表明市场上存在信息的学习者,需要对引起PIN增加的原因进行更准确的分析。     

英汉情态助动词语法及语义表达方式的对比

情态助动词是表达情态的重要手段,英语和汉语情态助动词有不同的语法和语义表达形式。根据Huddleston和Palmer关于情态助动词的理论框架,英语和汉语情态助动词被同时纳入否定、倒装、替代和强调四个语法特征进行对比,发现汉语在倒装方面与英语有很大差异,但是在其他三个特点上,均与英语具有共性。然后又将它们纳入意愿、可能和必须三个语义范畴,结合相应的语料对比、分析,发现它们的意义表达形式在三个语义范畴中表现有共性和个性。     

运用核Fisher鉴别分析和MPM分类器的入侵检测

为了提高分类器的正确率和减少训练时间,将特征提取技术与分类算法结合,提出了一种基于核Fisher鉴别分析和最小极大概率机算法的入侵检测算法。利用核Fisher鉴别分析技术提取关键特征,运用最小极大概率机对提取特征后的数据进行分类,采用离线数据集KDDCUP99进行实验。实验结果表明,该算法是可行和有效的,使分类性能和训练时间都得到了提高。     

民生工程建设综合评价研究

民生问题是构建和谐社会的关键,也是政府工作的基本着力点。在前期研究构建的指标体系的基础上,运用拉开档次评价法和逐层序关系分析法对我国31个省市自2006－2012年的民生工程建设状况进行了动态综合评价,并用时序几何平均算子（TOWGA）进行了二次加权得到综合评价的总排名,最后对各地区的排序变化进行归纳、分析。