We propose Adaptive Incremental Mixture Markov chain Monte Carlo (AIMM), a novel approach to sample from challenging probability distributions defined on a general state-space. Typically, adaptive MCMC methods recursively update a parametric proposal kernel with a global rule; by contrast AIMM locally adapts a non-parametric kernel. AIMM is based on an independent Metropolis-Hastings proposal d...

‎Abstract: In this paper, a new mixture modelling using the normal mean-variance mixture of Lindley (NMVL) distribution has been considered. The proposed model is heavy-tailed and multimodal and can be used in dealing with asymmetric data in various theoretic and applied problems. We present a feasible computationally analytical EM algorithm for computing the maximum likelihood estimates. T...

The efficiency of many speech processing methods rely on accurate modeling of the distribution of the signal spectrum and a majority of prior works suggest that the spectral components follow the Laplace distribution. To improve the probability distribution models based on our knowledge of speech source modeling, we argue that the model should in fact be a multiplicative mixture model, includin...

A new variational Bayesian learning algorithm for Student-t mixture models is introduced. This algorithm leads to (i) robust density estimation, (ii) robust clustering and (iii) robust automatic model selection. Gaussian mixture models are learning machines which are based on a divide-and-conquer approach. They are commonly used for density estimation and clustering tasks, but are sensitive to ...

background & aim: in the survival data with long-term survivors the event has not occurred for all the patients despite long-term follow-up, so the survival time for a certain percent is censored at the  end  of the  study.  mixture  cure  model  was  introduced  by boag,  1949  for  reaching  a  more efficient analysis of this set of data. because of some disadvantages of this model non-mixtur...

In standard interval mapping of quantitative trait loci (QTL), the QTL effect is described by a normal mixture model. At any given location in the genome, the evidence of a putative QTL is measured by the likelihood ratio of the mixture model compared to a single normal distribution (the LOD score). This approach can occasionally produce spurious LOD score peaks in regions of low genotype infor...

MOTIVATION The occurrence of false positives and false negatives in a microarray analysis could be easily estimated if the distribution of p-values were approximated and then expressed as a mixture of null and alternative densities. Essentially any distribution of p-values can be expressed as such a mixture by extracting a uniform density from it. RESULTS The occurrence of false positives and...

A statistical inversion method is proposed for the photon–photoelectron-counting statistics in quantum key distribution experiment. With the statistical viewpoint, this problem is equivalent to the parameter estimation for an infinite binomial mixture model. The coarse-graining idea and Bayesian methods are applied to deal with this ill-posed problem, which is a good simple example to show the ...

The mixture of Gaussian distributions, a soft version of k-means ( [2]), is considered a stateof-the-art clustering algorithm. It is widely used in computer vision for selecting classes, e.g., color[4, 1, 5],texture[1, 9], shapes [12, 10]. In this algorithm, each class is described by a Gaussian distribution, defined by its mean and covariance. The data is described by a weighted sum of these G...