CALL FOR PAPERS
2nd Special Issue on MIXTURE MODELS
Econometrics and Statistics, Part B: Statistics
http://www.elsevier.com/locate/ecosta
We are inviting submissions for a 2nd special issue of the journal
Econometrics and Statistics (Part B: Statistics) in Mixture
Models. Mixture models are very popular for classification, in the
broad sense, and analyses involving latent variables; however, their
use is not limited to these fields. Other uses can be found in
survival analysis, smoothing, and empirical Bayes, to mention but a
few areas. Over the past few years, mixture models have been
intensively researched. This work is spread across theory,
implementation, and application. Despite their growing popularity and
the modelling flexibility that they offer, mixture model-based
approaches come with a number of challenges. For one, parameter
estimation is troublesome because the likelihood surface is
notoriously difficult, with many singularities and local maxima.
Iterative parameter estimation is almost always required, with
variants of the EM algorithm remaining the most popular approaches.
That said, other approaches such as variational approximations and MM
algorithms are gaining traction. Determining the number of components
and, more generally, model selection are also research directions of
significant interest. Other uses can be found in food authenticity
studies, medicine, the social sciences, nutrigenomics, and gene
expression studies.
Key research areas in mixture modelling include:
- Parameter Estimation
- Hypothesis Testing
- Categorical Data Analysis
- Identifiability Problems
- Cluster-Weighted Models
- Model Selection
- Classification and Clustering
- Mixtures of (Generalized) Linear Models
- Bayesian Approaches
- Non-Gaussian Mixtures
- Mixtures of Profile Likelihoods
- Dimension Reduction
In order to be considered for publication the papers should have a
significant novel component pertaining to Mixture Models. Original
methodological contributions to mixture modelling inspired in
applications will also be considered. Papers dealing, directly or
indirectly, with theoretical, computational and technical elements are
particularly encouraged. Authors who are uncertain about the
suitability of their papers should contact the editors. All
submissions must contain original unpublished work that is not being
considered for publication elsewhere.
Submissions will be refereed according to standard procedures for
Econometrics and Statistics. Information about the journal can be
found at http://www.elsevier.com/locate/ecosta.
The deadline for submissions is 20 August 2020. However, papers can
be submitted at any time and once they are received, they will enter
the editorial system immediately.
Papers for the special issue should be submitted using the Elsevier
Electronic Submission tool EM:
https://www.editorialmanager.com/ecosta/.
In the EM, please choose the special issue on Mixture Models.
The special issue editors:
Salvatore Ingrassia, University of Catania, Italy.
E-mail: [log in to unmask]
Tsung-I Lin, National Chung Hsing University, Taiwan.
E-mail: [log in to unmask]
You may leave the list at any time by sending the command
SIGNOFF allstat
to [log in to unmask], leaving the subject line blank.
|