Search Results - subject:"EM Algorithm"

Estimation of generalized linear latent variable models via fully exponential Laplace approximation

Bianconcini, Silvia; Cagnone, Silvia - In: Journal of Multivariate Analysis 112 (2012) C, pp. 183-193

Latent variable models represent a useful tool in different fields of research in which the constructs of interest are not directly observable. In such models, problems related to the integration of the likelihood function can arise since analytical solutions do not exist. Numerical...

Persistent link: https://www.econbiz.de/10010594239

Constrained EM algorithm with projection method

Takai, Keiji - In: Computational Statistics 27 (2012) 4, pp. 701-714

the conventional EM algorithm. This new step is easy to implement, first because only the first derivatives of the object … apply the P-step in addition to the conventional EM algorithm to the two illustrative examples. The first example has a … function and the constraint function are necessary, and secondly, because the P-step is carried out after the conventional EM …

Persistent link: https://www.econbiz.de/10010600757

Dimensionality of the Latent Structure and Item Selection Via Latent Class Multidimensional IRT Models

Bartolucci, F.; Montanari, G.; Pandolfi, S. - In: Psychometrika 77 (2012) 4, pp. 782-802

With reference to a questionnaire aimed at assessing the performance of Italian nursing homes on the basis of the health conditions of their patients, we investigate two relevant issues: dimensionality of the latent structure and discriminating power of the items composing the questionnaire. The...

Persistent link: https://www.econbiz.de/10010600770

Bayesian analysis of quantile regression for censored dynamic panel data

Kobayashi, Genya; Kozumi, Hideo - In: Computational Statistics 27 (2012) 2, pp. 359-380

Persistent link: https://www.econbiz.de/10010558263

Likelihood ratio inference for mean residual life

Shen, Junshan; Liang, Wei; He, Shuyuan - In: Statistical Papers 53 (2012) 2, pp. 401-408

Persistent link: https://www.econbiz.de/10010558274

Space alternating penalized Kullback proximal point algorithms for maximizing likelihood with nondifferentiable penalty

Chrétien, Stéphane; Hero, Alfred; Perdry, Hervé - In: Annals of the Institute of Statistical Mathematics 64 (2012) 4, pp. 791-809

Persistent link: https://www.econbiz.de/10010558358

Robust Deviance Information Criterion for Latent Variable Models

Li, Yong; Zeng, Tao; Yu, Jun - School of Economics, Singapore Management University - 2012

data augmentation. While the later quantity is difficult to compute, the expectation - maximization (EM) algorithm …

Persistent link: https://www.econbiz.de/10010562112

Approximation of the variance gamma model with a finite mixture of normals

Loregian, Angela; Mercuri, Lorenzo; Rroji, Edit - In: Statistics & Probability Letters 82 (2012) 2, pp. 217-224

We investigate the possibility of approximating the variance gamma distribution with a finite mixture of normals. Therefore, we apply this result to derive a simple historical estimation procedure by means of the Expectation Maximization algorithm.

Persistent link: https://www.econbiz.de/10010571815

Theoretical and practical considerations on the convergence properties of the Fisher-EM algorithm

Bouveyron, Charles; Brunet, Camille - In: Journal of Multivariate Analysis 109 (2012) C, pp. 29-41

The Fisher-EM algorithm has been recently proposed in Bouveyron and Brunet (2012) [5] for the simultaneous … discriminative subspace with a low intrinsic dimension. Although the Fisher-EM algorithm is based on the EM algorithm, it does not … therefore questionable. The aim of this work is twofold. First, the convergence of the Fisher-EM algorithm is studied from the …

Persistent link: https://www.econbiz.de/10010572288

On estimation of a heteroscedastic measurement error model under heavy-tailed distributions

Cao, Chun-Zheng; Lin, Jin-Guan; Zhu, Xiao-Xin - In: Computational Statistics & Data Analysis 56 (2012) 2, pp. 438-448

follow scale mixtures of normal (SMN) distribution. We develop the EM algorithm to compute the maximum likelihood estimates …

Persistent link: https://www.econbiz.de/10010574470