Definitive Screening Design:An Important Class of Circulant-Type Design

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：njcdst

【摘要】

：

【作者】

：

Frederick Kin Hing Phoa Yuan-Lung Lin Tai-Chi Wang

【机构】

：

Institute of Statistical Science,Academia Sinica,Taipei 11529,Taiwan

【出处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

Definitive Screening Designs Conference Matrices Hadamard Matrices General Suppl

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

　　Jones and Nachtsheim(2011)proposed a new class of three-level screening designs called Definitive Screening(DS)designs,and it received much attention due to its appealing statistical properties.This work consists of two parts.The first part reviews the systematic construction of three-level DS designs proposed in Phoa and Lin(2015),which utilized the circulant property of the designs.The second part proposed a similar systematic construction method for two-level DS designs.

其他文献

Constructing Disease Onset Signatures Using High-Dimensional Network-Structured Biomarkers

Potential disease-modifying therapies for neurodegenerative disorders need to be introduced prior to the symptomatic stage in order to be effective.However,current diagnosis of neurological disorders

会议

Association between temporal trends in biomarkers for HIV progression

For some HIV studies,we are interested in the temporal trends of HIV progression related biomarkers,especially the association between two temporal trends.However,the biological mechanisms for many bi

会议

BiomarkerMixed-effects modelNonparametric regression

EXTRA HIGH-DIMENSIONAL LINEAR ODE MODEL SELECTION AND PARAMETER ESTIMATION:A MATRIX-BASED APPROACH

Ordinary differential equations(ODEs)are widely used to model the dynamic behavior of a complex system.Parameter estimation and variable selection for a "Big System" with high-dimensional linear ODEs

会议

High-dimensional dataModel selectionSeparable least squaresSimilarity transfo

Planning Sample Size Using MMRM in Confirmatory Trials

When planning sample size in confirmatory trials,the sample size is estimated from hypothesized effect size of the underlying study treatment.In order to account for potential dropout during the study

会议

MMRMsample sizestudy designmissing data

SOME SPATIO-TEMPORAL MODELLING PROBLEMS AND RECENT ADVANCES

Spatio-temporal modelling is a must in research in many fields of science and social science.It is always a challenge to model spatio-temporal data,since they vary over space and time,and usually have

会议

Spatio-temporal modellingspatio-temporal interactionmissing observationsBayes

USING LOGISTIC REGRESSION TO PREDICT UNDERAGE ALCOHOL CONSUMPTION BY SECONDARY SCHOOL STUDENTS

In this study,we approach the major problem of underage alcohol consumption by secondary school students through statistics.Underage drinking is when anyone under the minimum age of 21 drinks alcohol.

会议

logistic regressionclassificationgradient ascentoptimizationdata mining

A SYSTEMATIC PROCEDURE FOR SQUARE RANDOM LATTICE SAMPLING

The selection procedure,in which probability of selection for each unit of the population into the sample is same,almost fails to achieve the goals of a specified sampling theory.The selection procedu

会议

Controlled SamplingLatin SquaresLattice SamplingRelative PrecisionSimple Ran

Weighted Statistic in Detecting Faint and Sparse Alternatives for High-dimensional Covariance Matric

This paper considers testing equality of two population covariance matrices when the data dimension p diverges with the sample size n(p/n→c>0).We propose a weighted test statistic which is data-driven

会议

Linear Spectral StatisticLarge random matrix theoryStieltjes transformFaint a

High Dimensional Correlation Matrices:CLT and Its Applications

Statistical inferences for sample correlation matrices are important in high dimensional data analysis.Motivated by this,this paper establishes a new central limit theorem(CLT)for a linear spectral st

会议

Central limit theoremequivalence testhigh dimensional correlation matrixindep

Bayesian Modeling and Inference for Nonignorably Missing Longitudinal Binary Response Data with Appl

Missing data are frequently encountered in longitudinal clinical trials.To better monitor and understand the progress over time,we must handle the missing data appropriately and thus determine whether

会议

Probit ModelLatent VariableJeffrey's PriorIdentifiabilityDIC and LPML

Definitive Screening Design:An Important Class of Circulant-Type Design

其他学术论文