Nonparametric regression for Zero-Inflated Poisson model

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：dadada123sasasa

【摘要】

：

The Zero-inflated Poisson model is used to fit the counting data that contain excess zeros.This article mainly discusses the situation that the mean parameter of Poisson distribution is assumed to be

【作者】

：

Zuo Guoxin Wan Tang Xiao Yao

【机构】

：

Central China Normal University,Wuhan 430079,China n

【出处】

：

上海交通大学

【发表日期】

：

2016年4期

【关键词】

：

Zero-inflated poissonlocal local polynomial kernel regressionEM algorithmintegra

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

　　The Zero-inflated Poisson model is used to fit the counting data that contain excess zeros.This article mainly discusses the situation that the mean parameter of Poisson distribution is assumed to be a smoothing function.Local polynomial regression method is applied to fit the mean function.Numerical simulations are adopted to illustrate the performance of the method.Finally,real data analysis is discussed via this method.

其他文献

A Bayesian prediction model between a biomarker and the clinical endpoint for dichotomous variables

Early biomarkers are often helpful for early efficacy evaluation of clinical endpoints even if the biomarker cannot replace clinical outcome as a surrogate.

会议

BiomarkerBayesian modelpredictive modelingbinary endpointvaccine development

Transforming the empirical likelihood towards better accuracy

Under-coverage has been a long-standing issue with the empirical likelihood confidence regions.

会议

empirical likelihoodtransformed empirical likelihoodcoverage accuracy

A Simulation Study for Estimating Average Causal Effect of Latent Class

Unlike randomized trial,statistical strategies for inferring the unbiased causal relationship are required in the observational studies.

会议

Average causal effectCausal inferenceLatent class analysisPropensity score

Parallelized Adaptive Rejection Metropolis Sampling on the Utility of Graphics Cards

Adaptive rejection Metropolis sampling(ARMS)is one of the popular tools for solving many modern-day statistical,optimization and computational problems.

会议

parallel computingGPU computingMarkov chain Monte Carlo (MCMC)Adaptive reject

On the Relationship between Missing Data and Causal Inference

会议

False Discovery Rate Control for Multiple Change-point Detection

会议

PETER HALL:HKU AND TIME SERIES

Peter Hall visited the Department of Statistics and Actuarial Science,University of Hong Kong almost annually since the late nineties of the last century.In memorizing this great colleague we will rev

会议

On Exact Inferences Using Binary Data in Two or Multi-stage Designs

When establish an effective treatment using binary data from a two-stage design,one-sided tests for a proportion p are employed.

会议

Abel transformationCoverage probabilityPowerSmallest lower one-sided interval

FUSION LEARNING IN DATA INTEGRATION

Combining datasets collected from similar studies becomes increasingly popular in biomedical research to achieve larger sample sizes and greater statistical power.

会议

Friction of fusionfused Lassoheterogeneitymeta analysis

An Autologistic Regression Model for Binary Classification of Hyperspectral Remote Sensing Imagery

Remote sensing images from Earth-orbiting satellites are a potentially rich data source for monitoring atmospheric health hazards that cover large geographic regions.

会议

logistic regressionmarkov random fieldsimage segmentationsatellite imagery

Nonparametric regression for Zero-Inflated Poisson model

与本文相关的学术论文