• 不 限
  • 期刊论文
  • 硕博论文
  • 会议论文
  • 报 纸
  • 英文论文
  2. 您的位置
  3. 首页
  4. 会议论文
  5. The assembly and decomposition(AD)method for constructing separable minorizing functions in a class

The assembly and decomposition(AD)method for constructing separable minorizing functions in a class

来源 :上海交通大学 | 被引量 : 0次 | 上传用户：jayzhoujian
【摘 要】
：
The minorization–maximization(MM)principle is an important and useful tool in the design of optimization algorithms for calculating the maximum likelihood estimates(MLE)of parameters in statistics bec
【作 者】
：
Xi-Fen HUANG Guo-Liang TIAN Jinfeng XU 
【机 构】
：
Department of Statistics and Actuarial Science,The University of Hong Kong,Pokfulam Road,Hong Kong,P
【出 处】
：
上海交通大学
【发表日期】
：
2016年4期
【关键词】
：
MM algorithm minorizing function decomposition technique assembly technique Maxi 
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 minorization–maximization(MM)principle is an important and useful tool in the design of optimization algorithms for calculating the maximum likelihood estimates(MLE)of parameters in statistics because of its conceptual simplicity,ease of implementation and numerical stability just like an expectation–maximization(EM)algorithm.
其他文献
A Joint Modeling Approach for Treatment Response and Baseline Imaging data
There have been a lot of interests in using neuroimaging approaches to help guide clinicians in selecting treatment for patients of major depressive disorders and understand placebo response.
会议
Dimension reductionJoint modellingPlacebo and treatment responsesHigh-Dimensi
Current Status Data in the Presence of a Terminal Event
We consider nonparametric estimation of current status data in the presence of a terminal event.This type of data often arises in biomedical studies,where the subject is scheduled to be examined for t
会议
Composite endpointinterval censoringnonparametric maximum likelihoodsemicompe
A Wavelet-based Test for Serial Correlation
A new test for serial correlation is proposed based on the quantity called wavelet variance.With the advantage of not needing to test a series of lags,the proposed test uses the wavelet variance vecto
会议
Portmanteau testsIndependenceWhite NoiseWavelet VarianceGMWM
Conditional Quantile Regression Tree with Rank Score Statistics
Regression Trees have been widely used as a powerful and flexible statistical learning tool when one has a large number of covariates.
会议
Conditional quantile regressionTree
Zero-inflated Quantile Regression and It's Application in NOMAS
The Northern Manhattan Study(NOMAS)is a population-based study designed to evaluate the impact of medical,socio-economic,and other risk factors on the incidence of vascular disease in a multi-ethnic,s
会议
Quantile regressionZero-inflated outcomesConstrained smoothing
Sparse Cointegrating Market-Neutral Portfolio
Cointegration is one of the most important topics in economic and finance in the last decade,because it does not only study the long-run equilibrium among two or more economic time series but also for
会议
adaptive lassocointegrationmarket-neutralportfolios
LONG TIME BEHAVIOUR OF STOCHASTIC DIFFERENTIAL EQUATION WITH SINGULAR COEFFICIENTS
We prove the long time behavior such as exponential ergodicity and Donsker-Varadhan type large deviation for a family of Markov processes Xt governed by a stochastic differential equation(SDE)with sin
会议
Stochastic differential equation with singular coefficientsPartial-Zvonkin'
Assessing the Power of Independent Samples t,Mann-Whitney and Van der Warden Tests for Likert Type D
Introduction: Likert type data is frequently used in social and medical sciences.Indeed when there is not an instrument to measure a continuous variable(such as happiness,pain,…)Likert points are inst
会议
independent samples t-testMann-Whitney testVan der Warden testLikert data
Data Adaptive Tail-index Regression
Tail-index is an important measure to gauge the heavy-tailed behavior of a distribution.The problem of estimation of a Tail-index from various types of data has become rather important.Tail-index regr
会议
AggregationBurr-XII distributionOrdinary least-squaresPareto-type of distribu
Non-parametric Test for Equality of Distributions of High-Dimensional Data
Its not uncommon to test the equality of the K distributions in high dimensional data.
会议