变系数模型的变量选择

文章基于变系数模型,研究了模型变量选择的问题.采用B样条函数逼近模型中的系数函数,结合LASSO、SCAD和MCP罚函数,利用组坐标下降算法进行变量选择.通过模拟比较了这三种罚函数的效果.模拟结果印证提出方法的有效性,并且得到MCP和SCAD优于LASSO.     

Logistic半参数变系数模型的变量选择

Logistic半参数变系数模型是半参数变系数模型的推广,它可以解决分类型因变量变系数模型的建模问题.文章利用B样条函数逼近非参数部分,引入LASSO、SCAD以及MCP惩罚函数,基于组坐标下降算法,对参数部分和非参数部分进行变量选择.最后进行了Monte Carlo模拟.     

变量选择方法在医疗保险赔付评估中的应用

在广义线性模型假设下,采用Lin的医疗费用模型,运用LASSO和SCAD方法对影响医疗费用的因素进行选择,并对两种方法的有效性进行了对比分析,从而得出影响医疗保险赔付的重要因素,解决了高维变量带来的一系列问题。实例分析中,由于两种方法注重的统计性质不同,选择出的解释变量略微不同,但通过分析发现,两种结果都具有良好的解释性,反映了影响医疗保险赔付的重要信息。     

Cox模型中基于Model-X Knockoffs的高维控制变量选择方法

在生物医学、临床试验和流行病学等领域的研究中，由于获得生存数据的试验设计、观测时间的局限，以及观测对象在进入或退出试验时的个体差异等方面的原因，与所关注事件的发生时间相关的数据经常存在右删失。基于右删失生存数据解析协变量和生存时间的关系时，应用最为广泛的统计模型是Cox模型。随着科学技术的进步，数据收集变得越来越容易，导致数据库规模越来越大、复杂性越来越高，数据的维度通常可以达到成百上千维，甚至更高。文章提出一种Cox模型中基于Model-X Knockoffs的高维控制变量选择方法。首先基于Knockoffs框架建立一个Knockoffs变量，并基于原始协变量和其相应的Knockoffs变量构造一个正则化的目标函数，然后通过求解目标函数的最优解构造一个统计量和基于数据的阈值，最后进行变量选择。模拟分析和实证研究结果表明：所提方法可以在变量选择的同时提供可靠的FDR控制，优于传统的LASSO方法。     

有监督Group MCP方法的稳健性研究

采用模拟研究的方法,分别在回归预测和分类判别两种环境中讨论有监督Group MCP方法在不同结构错误率下进行变量选择和结果预测的稳健性,并通过实例分析讨论本研究的实用价值。研究结果显示:忽略解释变量的内部结构进行变量选择会导致很多重要解释变量被疏漏,而有监督Group MCP方法考虑了解释变量的内部结构,在结构错误率低于5%时会以不低于98%的概率选出有效解释变量,并尽量降低冗余变量被选择的可能性。此研究成果为有监督Group MCP方法的合理使用奠定了基础。     

广义线性模型下ERIC方法的调节参数选择

变量选择是处理高维统计模型的基本方法,在回归模型的变量选择中SCAD惩罚函数不仅可以很好地选择出正确模型,同时还可以对参数进行估计,而且还具有oracle性质,但这些良好的性质是基于选择出一个合适的调节参数。目前国内关于调节参数选择方面大多是对于变量选择问题的研究,针对广义线性模型基于SCAD惩罚使用新方法 ERIC准则进行调节参数的选择,并证明在一定条件下经过该准则选择的模型具有一致性。模拟与实证分析结果表明,ERIC方法在选择调节参数方面优于传统的CV准则、AIC准则和BIC准则。     

基于实证的社会生态评价指标的变量选择

文章提出了评价社会生态的指标体系.通过对武汉临空港经济技术开发区的实证调查研究,以乐业指数为例,运用套索(LASSO)方法对数据作重要变量的选择来降维和简化模型,再用传统Logistic回归建模和做参数估计,分析了影响群众满意度的一些重要影响因素及其效应.     

两维异质性面板分位数模型的双惩罚回归方法

文章关注系数具有两维异质性结构的面板分位数模型,基于SCAD惩罚函数和MCP惩罚函数提出双惩罚最小加权绝对偏差目标函数,同时进行参数估计和两维异质性结构识别。利用ADMM算法求解目标函数,并使用BIC信息准则通过网格搜索选择最优调节参数。根据蒙特卡洛模拟结果验证了所提方法的有限样本性质,最后使用实际数据检验了其应用效果。研究结果表明：所提出的方法能够准确识别两维异质性结构,并且Post估计量的参数估计精确度接近于Oracle估计量。     

基于偏好变量的指数跟踪方法

考虑到在进行指数跟踪时影响强度大并且流动性好的成份股往往是被偏好的,结合股票市场的网络结构和指数的编制规则,提出基于偏好变量的指数跟踪方法;对沪深300指数进行实证分析,从跟踪偏离度、平均超额收益和年跟踪误差三方面对新方法进行评估,并与非负LASSO模型进行对比分析。实证结果显示,新方法不仅优于非负LASSO模型,而且优于市场上大多数指数基金。     

大数据的整合分析方法

大数据具有数据来源差异性、高维性及稀疏性等特点,如何挖掘数据集间的异质性和共同性并降维去噪是大数据分析的目标与挑战之一。整合分析（Integrative Analysis）同时分析多个独立数据集,避免因地域、时间等因素造成的样本差异而引起模型不稳定,是研究大数据差异性的有效方法。它的特点是将每个解释变量在所有数据集中的系数视为一组,通过惩罚函数对系数组进行压缩,研究变量间的关联性并实现降维。本文从同构数据整合分析、异构数据整合分析以及考虑网络结构的整合分析三方面梳理了惩罚整合分析方法的原理、算法和研究现状。统计模拟发现,在弱相关、一般相关和强相关三种情形下, Group Bridge、 Group MCP、Composite MCP都表现良好,其中 Group Bridge的假阳数最低且最稳定。最后,将整合分析用于研究具有来源差异性的新农合家庭医疗支出,以及具有超高维、小样本等大数据典型特征的癌症基因数据,得到了一些有意义的结论。     

Robust variable selection in modal varying-coefficient models with longitudinal

In this article we present a robust and efficient variable selection procedure by using modal regression for varying-coefficient models with longitudinal data. The new method is proposed based on basis function approximations and a group version of the adaptive LASSO penalty, which can select significant variables and estimate the non-zero smooth coefficient functions simultaneously. Under suitable conditions, we establish the consistency in variable selection and the oracle property in estimation. A simulation study and two real data examples are undertaken to assess the finite sample performance of the proposed variable selection procedure.     

Estimation and variable selection in partial linear single index models with error-prone linear covariates

We study the estimation and variable selection for a partial linear single index model (PLSIM) when some linear covariates are not observed, but their ancillary variables are available. We use the semiparametric profile least-square based estimation procedure to estimate the parameters in the PLSIM after the calibrated error-prone covariates are obtained. Asymptotic normality for the estimators are established. We also employ the smoothly clipped absolute deviation (SCAD) penalty to select the relevant variables in the PLSIM. The resulting SCAD estimators are shown to be asymptotically normal and have the oracle property. Performance of our estimation procedure is illustrated through numerous simulations. The approach is further applied to a real data example.     

Robust modal estimation and variable selection for single-index varying-coefficient models

In this article, we present a new efficient iteration estimation approach based on local modal regression for single-index varying-coefficient models. The resulted estimators are shown to be robust with regardless of outliers and error distributions. The asymptotic properties of the estimators are established under some regularity conditions and a practical modified EM algorithm is proposed for the new method. Moreover, to achieve sparse estimator when there exists irrelevant variables in the index parameters, a variable selection procedure based on SCAD penalty is developed to select significant parametric covariates and the well-known oracle properties are also derived. Finally, some numerical examples with various distributed errors and a real data analysis are conducted to illustrate the validity and feasibility of our proposed method.     

Shrinkage and Penalty Estimators of a Poisson Regression Model

In this paper we propose Stein‐type shrinkage estimators for the parameter vector of a Poisson regression model when it is suspected that some of the parameters may be restricted to a subspace. We develop the properties of these estimators using the notion of asymptotic distributional risk. The shrinkage estimators are shown to have higher efficiency than the classical estimators for a wide class of models. Furthermore, we consider three different penalty estimators: the LASSO, adaptive LASSO, and SCAD estimators and compare their relative performance with that of the shrinkage estimators. Monte Carlo simulation studies reveal that the shrinkage strategy compares favorably to the use of penalty estimators, in terms of relative mean squared error, when the number of inactive predictors in the model is moderate to large. The shrinkage and penalty strategies are applied to two real data sets to illustrate the usefulness of the procedures in practice.     

COORDINATE DESCENT ALGORITHMS FOR NONCONVEX PENALIZED REGRESSION, WITH APPLICATIONS TO BIOLOGICAL FEATURE SELECTION

A number of variable selection methods have been proposed involving nonconvex penalty functions. These methods, which include the smoothly clipped absolute deviation (SCAD) penalty and the minimax concave penalty (MCP), have been demonstrated to have attractive theoretical properties, but model fitting is not a straightforward task, and the resulting solutions may be unstable. Here, we demonstrate the potential of coordinate descent algorithms for fitting these models, establishing theoretical convergence properties and demonstrating that they are significantly faster than competing approaches. In addition, we demonstrate the utility of convexity diagnostics to determine regions of the parameter space in which the objective function is locally convex, even though the penalty is not. Our simulation study and data examples indicate that nonconvex penalties like MCP and SCAD are worthwhile alternatives to the lasso in many applications. In particular, our numerical results suggest that MCP is the preferred approach among the three methods.     

Random effects selection in generalized linear mixed models via shrinkage penalty function

In this paper, we discuss the selection of random effects within the framework of generalized linear mixed models (GLMMs). Based on a reparametrization of the covariance matrix of random effects in terms of modified Cholesky decomposition, we propose to add a shrinkage penalty term to the penalized quasi-likelihood (PQL) function of the variance components for selecting effective random effects. The shrinkage penalty term is taken as a function of the variance of random effects, initiated by the fact that if the variance is zero then the corresponding variable is no longer random (with probability one). The proposed method takes the advantage of a convenient computation for the PQL estimation and appealing properties for certain shrinkage penalty functions such as LASSO and SCAD. We propose to use a backfitting algorithm to estimate the fixed effects and variance components in GLMMs, which also selects effective random effects simultaneously. Simulation studies show that the proposed approach performs quite well in selecting effective random effects in GLMMs. Real data analysis is made using the proposed approach, too.     

Paths Following Algorithm for Penalized Logistic Regression Using SCAD and MCP

In this article, we develop a generalized penalized linear unbiased selection (GPLUS) algorithm. The GPLUS is designed to compute the paths of penalized logistic regression based on the smoothly clipped absolute deviation (SCAD) and the minimax concave penalties (MCP). The main idea of the GPLUS is to compute possibly multiple local minimizers at individual penalty levels by continuously tracing the minimizers at different penalty levels. We demonstrate the feasibility of the proposed algorithm in logistic and linear regression. The simulation results favor the SCAD and MCP’s selection accuracy encompassing a suitable range of penalty levels.     

Variable Selection for Partially Linear Models with Randomly Censored Data

This article proposes a variable selection procedure for partially linear models with right-censored data via penalized least squares. We apply the SCAD penalty to select significant variables and estimate unknown parameters simultaneously. The sampling properties for the proposed procedure are investigated. The rate of convergence and the asymptotic normality of the proposed estimators are established. Furthermore, the SCAD-penalized estimators of the nonzero coefficients are shown to have the asymptotic oracle property. In addition, an iterative algorithm is proposed to find the solution of the penalized least squares. Simulation studies are conducted to examine the finite sample performance of the proposed method.     

Quadratic Approximation via the SCAD Penalty with a Diverging Number of Parameters

The high-dimensional data arises in diverse fields of sciences, engineering and humanities. Variable selection plays an important role in dealing with high dimensional statistical modelling. In this article, we study the variable selection of quadratic approximation via the smoothly clipped absolute deviation (SCAD) penalty with a diverging number of parameters. We provide a unified method to select variables and estimate parameters for various of high dimensional models. Under appropriate conditions and with a proper regularization parameter, we show that the estimator has consistency and sparsity, and the estimators of nonzero coefficients enjoy the asymptotic normality as they would have if the zero coefficients were known in advance. In addition, under some mild conditions, we can obtain the global solution of the penalized objective function with the SCAD penalty. Numerical studies and a real data analysis are carried out to confirm the performance of the proposed method.