Robust estimation and variable selection in censored partially linear additive models

来源 :中国现场统计研究会 | 被引量 : 0次 | 上传用户：qq540531049

【摘要】

：

In this paper,we consider a new estimation in censored partially linear additive models in which the nonparametric components are approximated by polynomial spline.

【作者】

：

Huilan Liu Hu Yang Xiaochao Xia

【机构】

：

College of Mathematics and Statistics,Chongqing University

【出处】

：

中国现场统计研究会

【发表日期】

：

2015年3期

下载到本地 , 更方便阅读

下载此文赞助VIP

声明 : 本文档内容版权归属内容提供方 , 如果您对本文有版权争议 , 可与客服联系进行内容授权或下架

论文部分内容阅读

　　In this paper,we consider a new estimation in censored partially linear additive models in which the nonparametric components are approximated by polynomial spline.

其他文献

Estimation of the Cholesky decomposition in a conditional independent normal model with missing data

We investigate the problem of estimating the Cholesky decomposition in a conditional independent normal model with missing data.

会议

Adaptive elastic net and Separate Selection from Least Squares for ultra-high dimensional regression

This paper studies the asymptotic properties of the adaptive elastic net in ultra-high dimensional sparse linear regression models and proposes a new method called SSLS(Separate Selection from Least S

会议

On-line Monitoring Data Quality of High-dimensional Data Streams

In recent years,effective monitoring of data quality has increasingly attracted attention of researchers in the area of statistical process control(SPC).

会议

中国区域间行业收入差距的差异分析--基于相对剥夺理论及基尼系数的子群分解方法

基于相对剥夺理论，重新定义了基尼系数子群之间不平等的表达式，随后选取若干经济指标，将我国19个行业分为4类，通过基尼系数子群分解，测算全国行业收入差距基尼系数，以及群间和群内不平等对基尼系数的贡献，发现我国行业收入差距子群之间的不平等较为明显，其中第一个子群即民生服务产业相对于其他三个行业表现出明显相对剥夺感；第二子群即高新技术产业相对其他三个子群表现出明显的优越性，通过计算和比较不同地区行业收入

会议

行业收入差距相对剥夺基尼系数子群分解

基于谱核的流形学习算法

现代统计学习中的核方法通过某种非线性映射将原始数据嵌入到合适的高维特征空间；然后,利用通用的线性学习器在这个新的空间中分析和处理模式,核方法在生物化学领域已经获得了广泛的应用。在生物学中,SMILES是一种用ASCII字符串明确描述分子结构的规范。

会议

Rotated sphere packing designs

We propose a new class of space-filling designs called rotated sphere packing designs for computer experiments.

会议

Experimental DesignLatticeLow discrepancyMaximin distance designMinimax dist

Group-Combined P-value with Applications to Genetic Association Studies

Combined p-value is widely used in genetic association analysis to detect the connections between multiple locations of genetic mutation and complex diseases.

会议

Group-combined p-valuefamilywise error ratepowergenetic association study

Decompositions of BLUEs under a multiple partitioned linear model with partial parameter restriction

A linear model y=β+ε is often written in certain partitioned form in order to distinguish contributions of each regressor in the linear model,while some small models can be formulated associated with

会议

Partitioned linear modelsmall modelBest linear unbiased estimatordecompositio

乘积误差模型的不等式约束广义最小二乘估计

Engle(2002)提出的乘积误差模型(MEM)是适用于所有非负值金融时间序列变量建模的新模型。由于MEM具有与自回归条件持续期(ACD)模型类似的形式和性质，因此可同样采用拟极大似然估计法获得模型的参数估计。

会议

乘积误差模型不等式约束广义最小二乘拟极大似然估计蒙特卡罗模拟

Asymptotics and statistical inferences on independent and non-identically distributed bivariate Gaus

In modeling asymptotically dependent risks,the classical and tractable Gaussian framework is inadequate,since the componentwise maxima of bivariate Gaussian random vectors possess asymptotic independe

会议

Bivariate Gaussian random vectorMaximumLimiting distributionSecond-order expa

Robust estimation and variable selection in censored partially linear additive models

其他学术论文