File Download

There are no files associated with this item.

  Links for fulltext
     (May Require Subscription)
Supplementary

Article: Compositional inverse Gaussian models with applications in compositional data analysis with possible zero observations

TitleCompositional inverse Gaussian models with applications in compositional data analysis with possible zero observations
Authors
KeywordsCompositional inverse Gaussian distribution
EM algorithm
inverse Gaussian distribution
zero-truncated product Bernoulli distribution
Issue Date31-Jul-2023
PublisherTaylor and Francis Group
Citation
Journal of Statistical Computation and Simulation, 2023, v. 94, n. 2, p. 248-278 How to Cite?
Abstract

Compositional data (CoDa) often appear in various fields such as biology, medicine, geology, chemistry, economics, ecology and sociology. Although existing Dirichlet and related models are frequently employed in CoDa analysis, sometimes they may provide unsatisfactory performances in modelling CoDa as shown in our first real data example. First, this paper develops a multivariate compositional inverse Gaussian (CIG) model as a new tool for analysing CoDa. By incorporating the stochastic representation (SR), the expectation–maximization (EM) algorithm (aided by a one-step gradient descent algorithm) can be established to solve the parameter estimation for the proposed distribution (model). Next, zero observations may be often encountered in the real CoDa analysis. Therefore, the second aim of this paper is to propose a new model (called as ZCIG model) through a novel mixture SR based on both the CIG random vector and a so-called zero-truncated product Bernoulli random vector to model CoDa with zeros. Corresponding statistical inference methods are also developed for both cases without/with covariates. Two real data sets are analysed to illustrate the proposed statistical methods by comparing the proposed CIG and ZCIG models with existing Dirichlet and logistic-normal models.


Persistent Identifierhttp://hdl.handle.net/10722/337130
ISSN
2023 Impact Factor: 1.1
2023 SCImago Journal Rankings: 0.510
ISI Accession Number ID

 

DC FieldValueLanguage
dc.contributor.authorLiu, P-
dc.contributor.authorTian, G-
dc.contributor.authorYuen, KC-
dc.contributor.authorSun, Y-
dc.contributor.authorZhang, C-
dc.date.accessioned2024-03-11T10:18:20Z-
dc.date.available2024-03-11T10:18:20Z-
dc.date.issued2023-07-31-
dc.identifier.citationJournal of Statistical Computation and Simulation, 2023, v. 94, n. 2, p. 248-278-
dc.identifier.issn0094-9655-
dc.identifier.urihttp://hdl.handle.net/10722/337130-
dc.description.abstract<p><em>Compositional data</em> (CoDa) often appear in various fields such as biology, medicine, geology, chemistry, economics, ecology and sociology. Although existing Dirichlet and related models are frequently employed in CoDa analysis, sometimes they may provide unsatisfactory performances in modelling CoDa as shown in our first real data example. First, this paper develops a multivariate <em>compositional inverse Gaussian</em> (CIG) model as a new tool for analysing CoDa. By incorporating the <em>stochastic representation</em> (SR), the <em>expectation–maximization</em> (EM) algorithm (aided by a one-step gradient descent algorithm) can be established to solve the parameter estimation for the proposed distribution (model). Next, zero observations may be often encountered in the real CoDa analysis. Therefore, the second aim of this paper is to propose a new model (called as ZCIG model) through a novel mixture SR based on both the CIG random vector and a so-called zero-truncated product Bernoulli random vector to model CoDa with zeros. Corresponding statistical inference methods are also developed for both cases without/with covariates. Two real data sets are analysed to illustrate the proposed statistical methods by comparing the proposed CIG and ZCIG models with existing Dirichlet and logistic-normal models.<br></p>-
dc.languageeng-
dc.publisherTaylor and Francis Group-
dc.relation.ispartofJournal of Statistical Computation and Simulation-
dc.subjectCompositional inverse Gaussian distribution-
dc.subjectEM algorithm-
dc.subjectinverse Gaussian distribution-
dc.subjectzero-truncated product Bernoulli distribution-
dc.titleCompositional inverse Gaussian models with applications in compositional data analysis with possible zero observations-
dc.typeArticle-
dc.identifier.doi10.1080/00949655.2023.2242550-
dc.identifier.scopuseid_2-s2.0-85166679086-
dc.identifier.volume94-
dc.identifier.issue2-
dc.identifier.spage248-
dc.identifier.epage278-
dc.identifier.eissn1563-5163-
dc.identifier.isiWOS:001038085600001-
dc.identifier.issnl0094-9655-

Export via OAI-PMH Interface in XML Formats


OR


Export to Other Non-XML Formats