A modified EM algorithm for mixture models based on Bregman divergence

The EM algorithm is a sophisticated method for estimating statistical models with hidden variables based on the Kullback–Leibler divergence. A natural extension of the Kullback–Leibler divergence is given by a class of Bregman divergences, which in general enjoy robustness to contamination data in statistical inference. In this paper, a modification of the EM algorithm based on the Bregman divergence is proposed for estimating finite mixture models. The proposed algorithm is geometrically interpreted as a sequence of projections induced from the Bregman divergence. Since a rigorous algorithm includes a nonlinear optimization procedure, two simplification methods for reducing computational difficulty are also discussed from a geometrical viewpoint. Numerical experiments on a toy problem are carried out to confirm appropriateness of the simplifications.     

Clustering of contingency table and mixture model

Basing cluster analysis on mixture models has become a classical and powerful approach. It enables some classical criteria such as the well-known k-means criterion to be explained. To classify the rows or the columns of a contingency table, an adapted version of k-means known as Mndki2, which uses the chi-square distance, can be used. Unfortunately, this simple, effective method which can be used jointly with correspondence analysis based on the same representation of the data, cannot be associated with a mixture model in the same way as the classical k-means algorithm. In this paper we show that the Mndki2 algorithm can be viewed as an approximation of a classifying version of the EM algorithm for a mixture of multinomial distributions. A comparison of the algorithms belonging in this context are experimentally investigated using Monte Carlo simulations.     

Analysis of two-sample censored data using a semiparametric mixture model

In this article we study a semiparametric mixture model for the two-sample problem with right censored data. The model implies that the densities for the continuous outcomes are related by a parametric tilt but otherwise unspecified. It provides a useful alternative to the Cox （1972） proportional hazards model for the comparison of treatments based on right censored survival data. We propose an iterative algorithm for the semiparametric maximum likelihood estimates of the parametric and nonparametric components of the model. The performance of the proposed method is studied using simulation. We illustrate our method in an application to melanoma.     

Self-decomposability of weak variance generalised gamma convolutions

Weak variance generalised gamma convolution processes are multivariate Brownian motions weakly subordinated by multivariate Thorin subordinators. Within this class, we extend a result from strong to weak subordination that a driftless Brownian motion gives rise to a self-decomposable process. Under moment conditions on the underlying Thorin measure, we show that this condition is also necessary. We apply our results to some prominent processes such as the weak variance alpha–gamma process, and illustrate the necessity of our moment conditions in some cases.     

偏t正态数据下混合线性联合位置与尺度模型的参数估计

偏t正态分布是分析尖峰,厚尾数据的重要统计工具之一.研究提出了偏t正态数据下混合线性联合位置与尺度模型,通过EM算法和Newton-Raphson方法研究了该模型参数的极大似然估计.并通过随机模拟试验验证了所提出方法的有效性.最后,结合实际数据验证了该模型和方法具有实用性和可行性.     

Failure rate of the inverse Gaussian-Weibull mixture model

Motivated by the idea that different causes of failure of a given system could lead to different failure distributions, a mixture of two-component distributions, one of which is the two-parameter Inverse Gaussian (IG) and the other the two-parameter Weibull (W), is proposed as a failure model. The IG-W mixture model convers several types of failure rates (FR's). It is shown that depending on the parameter values, the IG-W mixture model is capable of covering six different combinations of FR's, as one of the components has an upsidedown bathtub failure rate (UBTFR) or increasing failure rate (IFR) and the other component has a decreasing failure rate (DFR), constant failure rate (CFR), or IFR. A study is made for the mixed FR based on these six combinations.     

On estimating of the number of constituents of a finite mixture of continuous distributions

Summary Suppose thatH is a mixture of distributions for a given familyF A necessary and sufficient condition is obtained under whichH is, in fact, a finite mixture. An estimator of the number of distributions constituting the mixture is proposed assuming that the mixture is finite and its asymptotic properties are investigated.     

正态分布和瑞利分布混合情形下的参数估计及分类问题

学者往往用单一的分布模拟和拟合杂波,如正态分布、瑞利分布和威布尔分布等。然而在实际中,雷达杂波由多种类型的杂波组成,单一分布通常不能精确刻画雷达杂波规律,因此,应用混合分布模型对雷达杂波数据建模更准确。本文考虑用正态分布和瑞利分布的混合分布拟合杂波,并应用矩估计方法和基于EM算法的极大似然估计方法估计模型参数,最后,应用最大后验概率分类准则验证2种估计方法的分类准确率。通过数据模拟,得出极大似然估计的效果和分类准确率都要优于矩估计的估计效果和分类准确率。     

Heteroscedastic normal-exponential mixture models: Bayesian and classical approaches

In this paper, we introduce a Bayesian analysis for mixture of distributions belonging to the exponential family. As a special case we consider a mixture of normal exponential distributions including joint modeling of the mean and variance. We also consider joint modeling of the mean and variance heterogeneity. Markov Chain Monte Carlo (MCMC) methods are used to obtain the posterior summaries of interest. We also introduce and apply an EM algorithm, where the maximization is obtained applying the Fisher scoring algorithm. Finally, we also include analysis of real data sets to illustrate the proposed methodology.     

Maximum likelihood estimation in the multi-path change-point problem

Maximum likelihood estimators of the parameters of the distributions before and after the change and the distribution of the time to change in the multi-path change-point problem are derived and shown to be consistent. The maximization of the likelihood can be carried out by using either the EM algorithm or results from mixture distributions. In fact, these two approaches give equivalent algorithms. Simulations to evaluate the performance of the maximum likelihood estimators under practical conditions, and two examples using data on highway fatalities in the United States, and on the health effects of urea formaldehyde foam insulation, are also provided.This work was supported in part by the Natural Science and Engineering Council of Canada, and the Fonds pour la Formation de chercheurs et l'aide à la Recherche Gouvernment du Québec.Lawrence Joseph is also a member of the Department of Epidemiology and Biostatistics of McGill University.     

删失截断情形下失效率变点模型的Bayes参数估计

通过添加部分缺失寿命变量数据,得到了删失截断情形下失效率变点模型相对简单的似然函数.讨论了所添加缺失数据变量的概率分布和随机抽样方法.利用Monte Carlo EM算法对未知参数进行了迭代.结合Metropolis-Hastings算法对参数的满条件分布进行了Gibbs抽样,基于Gibbs样本对参数进行估计,详细介绍了MCMC方法的实施步骤.随机模拟试验的结果表明各参数Bayes估计的精度较高.     

Mixed proportional hazard models with continuous finite mixture unobserved heterogeneity: an application to Canadian firm survival

This paper proposes a methodology that accounts for the selection effect due to non‐random entry in duration models using latent‐class models. A mixed proportional hazard model with continuous finite mixture unobserved heterogeneity (MPH‐CFM) is introduced to correct for the potential bias induced by the selection effect. Conditions for identification, consistency, and asymptotic normality of the MPH‐CFM are provided. The estimator is used to investigate the duration of new entrant Canadian manufacturing firms. For the current application, the MPH‐CFM is compared with alternative duration models and found to be superior. Empirically, the results indicate that there are two classes of firms. Class I starts with high hazard and decreases non‐monotonically while Class II has a negligible hazard. These empirical results can be used to understand alternative models of firm dynamics. Copyright © 2017 John Wiley & Sons, Ltd.     

混合双重广义线性模型的参数估计

在实际应用中,不同类别的数据统计特性存在差异,所以对异质总体的研究非常有必要.基于总体一,二阶矩存在,利用双重广义线性模型对异质总体的不同子类数据的均值和散度同时建模,研究提出了混合双重广义线性模型.然后,利用EM算法构造了模型参数的最大扩展拟似然估计和最大伪似然估计.最后,通过随机模拟和实例研究,结果表明模型和方法的有效性和有用性.     

On modeling left-truncated loss data using mixtures of distributions

A new statistical methodology is developed for fitting left-truncated loss data by using the G-component finite mixture model with any combination of Gamma, Lognormal, and Weibull distributions. The EM algorithm, along with the emEM initialization strategy, is employed for model fitting. We propose a new grid map which considers the model selection criterion (AIC or BIC) and risk measures at the same time, by using the entire space of models under consideration. A simulation study validates our proposed approach. The application of the proposed methodology and use of new grid maps are illustrated through analyzing a real data set that includes left-truncated insurance losses.     

Parameter estimation of the WMTD model

The MTD （mixture transition distribution） model based on Weibull distribution （WMTD model） is proposed in this paper, which is aimed at its parameter estimation. An EM algorithm for estimation is given and shown to work well by some simulations. And bootstrap method is used to obtain confidence regions for the parameters. Finally, the results of a real example--predicting stock prices--show that the WMTD model proposed is able to capture the features of the data from thick-tailed distribution better than GMTD （mixture transition distribution） model.     

离子通道的混合密度参数估计与状态判别

本文针对多电导水平离子通道的由多个正态分布加权组成的混合分布特点,用EM迭代算法对混合分布中的参数进行极大似然估计,并在此基础上,利用混合分布中最可能的成分判断通道状态,从而还原通道潜在信号,克服了离子通道分析软件PCLAMP中参数估计与状态还原的缺陷。     

Asymptotic behavior of the stationary distribution in a finite QBD process with zero mean drift

We consider a finite QBD process with m levels. Assuming that the mean drift is 0, we obtain an asymptotic behavior as m→∞ in the stationary distribution , by finding an explicit expression for vector c. This solves the problem that was conjectured by Miyazawa et al. [Asymptotic behaviors of the loss probability for a finite buffer queue with QBD structure, 23 (2007) 79-95].     

基于Dirichlet分布有限混合模型的Bayes聚类

本文基于Dirichlet分布有限混合模型,提出了一种用于成分数据的Bayes聚类方法.采用EM算法获得模型参数的估计,用BIC准则确定类数,用类似于Bayes判别的方法对各观测分类.推导了计算公式,编写出程序.模拟研究结果表明,本文提出的方法有较好的聚类效果.     

偏正态数据下众数回归模型的统计诊断

为了更好地拟合偏态数据,充分提取偏态数据的信息,针对偏正态数据建立了众数回归模型,并基于Pena距离统计量对众数回归模型进行统计断研究,得到了众数回归模型的Pena距离表达式以及高杠杆异常点的诊断方法.利用EM算法与梯度下降法给出了众数回归模型参数的极大似然估计,根据数据删除模型计算似然距离、Cook距离和Pena距离统计量,绘制诊断统计图.通过Monte Carlo模拟试验和实例分析比较,说明文章提出的方法行之有效,并在一定条件下Pena距离对异常点或强影响点的诊断优于似然距离和Cook距离.