2. 您的位置
3. 首页
4. 会议论文
5. Using differential variability to increase the power of the homogeneity test in a two-sample problem

Using differential variability to increase the power of the homogeneity test in a two-sample problem

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：cerfa

【摘 要】

：

We consider a particular two-sample homogeneity testing problem which is often encountered in case-control studies with contaminated controls,or detecting a treatment effect when some subjects are not

【作 者】

：

Guanfu Liu Yuejiao Fu Pengfei Li Xiaolong Pu 

【机 构】

：

School of Statistics,East China Normal University,Shanghai 200241,China

【出 处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

Differential variability EM-test Homogeneity test Mixture models Two-sample prob 

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

　　We consider a particular two-sample homogeneity testing problem which is often encountered in case-control studies with contaminated controls,or detecting a treatment effect when some subjects are not affected by treatment in biological experiments.

其他文献

Pseudo-likelihood and bootstrapped pseudo-likelihood inference in logistic regression model with mis

Logistic regression is an important and widely used regression model for binary responses and is extensively used in many applied fields.

会议

Logistic regressionMisclassificationBootstrapEstimating equationConsistency

Rotation Survival Forest for High Dimensional Censored Data

In this study,we extend rotation forest to high dimensional censored time-to-event data analysis by combing random subspace,bagging and rotation forest.

会议

survival ensemblerotation forestcensored datahigh-dimensional data

Robust diagnostics for mixed continuous and categorical data with missing values

This paper applies the forward search to obtain robust log-likelihood values to detect the presence of outliers in a sample of mixed continuous and categorical data with missing values.

会议

Forward search algorithmmissing valuesmultiple outliersrobust diagnostics

U-STATISTICS FOR SOME MISSING DATA MODELS

For some commonly used censored data models,the U-statistic for estimating some functionals of the underlying distribution cannot be computed directly,as the corresponding kernel requires all original

会议

Conditional kernelincomplete data modelNPMLEU-statistics

Investigating differential variability for DNA methylation data

DNA methylation is a mechanism that regulates gene expression without changing genetic coding.Recently researchers found that DNA methylation marks that are differentially variable(DV)between cancer p

会议

Brown-Forsythe's testLevene's testlogistic regressionsystematic sim

Intermittency of Stochastic Partial Differential Equations

In this talk,we will mainly investigate the intermittent property to one-dimensional stochastic partial differential equation driven by an inhomogeneous Gaussian noises,which is deduced from the study

会议

Stochastic partial differential equationinhomogeneous noiseLyapunov exponents

LENGTH-BIAS CORRECTION IN ESTIMATING LIFETIME DISTRIBUTIONS

Length biased lifetime(or time-to-event)measurements can occur in a wide range of scientific investigations when cross-sectional sampling method is employed for collecting lifetime data.

会议

Cross-sectional samplingBirth and death processesLength-bias modelsLeft-trunc

A Peak-Over-Threshold Search Method for Global Optimization

A lot of problems in automatic control aim at optimizing complex systems.In this paper,we propose a new random search method,called peak-over-threshold search(POTS),for solving global optimization pro

会议

partition-based random searchglobal optimizationextreme value analysismetaheu

An adaptive Fishers method for combining information across samples

Motivated by the problem of detecting DNA copy number variations(CNV)in multiple samples,we propose an adaptive Fishers method for combining information across samples.

会议

CNVadaptive Fisher's methodrare/weak signal detection

Covariate Adjusted Spearman's Rank Correlation with Probability-Scale Residuals

It is often of interest to summarize the degree of association between two variables using a single number,the correlation coefficient.

会议

Partial correlationConditional correlationRank-based statisticSemiparametric