2. 您的位置
3. 首页
4. 会议论文
5. Nonparametric Variable Selection and Screening

Nonparametric Variable Selection and Screening

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：kinds1118

【摘 要】

：

This talk will cover two recently proposed nonparametric methods.In the first part,I will speak on a nonparametric shrinkage and selection estimator via the measurement error selection likelihood appr

【作 者】

：

Yichao Wu 

【机 构】

：

North Carolina State University,Raleigh,NC 27695,USA

【出 处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

bandwidth selection feature selection Nadaraya-Watson nonparametric regression s 

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

　　This talk will cover two recently proposed nonparametric methods.In the first part,I will speak on a nonparametric shrinkage and selection estimator via the measurement error selection likelihood approach recently proposed by Stefanski,Wu,and White.

其他文献

Out-of-sample equity premium prediction:a scenario analysis approach

We propose a method with a single predictor for equity premium prediction,in which three scenarios are defined as low,average,and high return scenarios respectively,with their occurrence assumed to fo

会议

Combination forecastequity premiumMarkov chainquantile regressionscenario an

Analysis of Event History Data in Forest Fire Control

In attempt to understand how fire behaviour is associated with environmental factors together with the fires location and starting time,we analyze a collection of lightning-caused forest fire records.

会议

coarsened event timeslongitudinal measuressemiparametric analysisspatio-tempo

A Nonparametric Regression Model for Panel Count Data

Panel count data are commonly encountered in analysis of recurrent events where the exact event times are unobserved.To accommodate the potential non-linear covariate effect,we consider a nonparametri

会议

Childhood wheezingEmpirical processMaximum pseudolikelihood estimatorRe-gress

Data Analysis and Control of the Transmission of Dengue in Guangzhou

An outbreak of dengue fever in Guangdong province in 2014 was the most serious ever recorded in China.Given the known positive relationship between the abundance of mosquitoes and the number of dengue

会议

Vector-borne diseaseInterventionClimateBreteau indexImmature

Multiscale Change Point Inference for Heterogeneuous Data-with Applications to Ion Channel Recording

We propose a new estimator H-SMUCE(heterogeneous simultaneous multiscale changepoint estimator)for the detection of multiple change-points of the signal in a heterogeneous gaussian regression model.A

会议

Change-point regressionDynamic programmingHonest confidence setsMultiscale me

Analysis of longitudinal association patterns of recurrent gap times

For recurrent event data,the gap times between two consecutive recurrent events are natural outcomes of interest in many applications.In long-term follow-up studies,it is of interest to study the poss

会议

Association measureConcordanceGap timesTemporal dependence

Bias-reduced moment estimators of Population Spectral Distribution and their applications

Covariance matrices play an essential role in multivariate and high-dimensional statistics.In this paper,we propose a series of bias-reduced moment estimators for the Population Spectral Distribution(

会议

ConsistencyLarge covariance matrixMoment estimatorPopulation spectral distrib

Bayesian Capabilities in SAS/STAT(R)Software

The use of Bayesian methods has become essentially important in modern statistical analysis,with applications in numerous scientific fields.In recent releases,SAS R has provided a wealth of tools for

会议

SAS/STAT softwareBayesianMCMCsimulation

SAVING SOCIAL SURVEYS? A CANADIAN PERSPECTIVE

Perhaps the second half of the twentieth century will be viewed as the golden age of survey sampling.In that period,in developed countries,there was a proliferation of social surveys on a broad range

会议

Survey samplingNonresponseSurvey infrastructureAdministrative data

A Robust Bayesian Dose-Finding Design for Phase Ⅰ/Ⅱ Clinical Trials

We propose a Bayesian phase Ⅰ/Ⅱ dose-finding trial design that simultaneously accounts for toxicity and efficacy.We model the toxicity and efficacy of investigational doses using a flexible Bayesian d

会议

Adaptive designBayesian methodUtilityTrade-offPhase Ⅰ/Ⅱ trial