File Download
 
Links for fulltext
(May Require Subscription)
  • Find via
 
Supplementary

Conference Paper: Compositional data, Bayesian inference and the modeling process
  • Basic View
  • Metadata View
  • XML View
TitleCompositional data, Bayesian inference and the modeling process
 
AuthorsBacon-Shone, J
 
Issue Date2011
 
CitationThe 4th International Workshop on Compositional Data Analysis (CoDaWork 2011), Girona, Spain, 9-13 May 2011. In Proceedings of the 4th CoDaWork, 2011 [How to Cite?]
 
AbstractStatistical modeling in practice encompasses both the exploratory process, which is an inductive scientific approach and the confirmatory modeling process, which uses the deductive scientific approach. This paper will focus primarily on the confirmatory modeling process. As the great applied statistician George Box, has famously said “all models are wrong, but some are useful”. My version would be “all models are wrong, but some are essential for progress”! While John Aitchison has changed the world of compositional data analysis, the world of Bayesian statistics has also changed dramatically thanks to the Gibbs sampler, which allows Bayesian analysis of complex non-linear models and particularly random effects models. The beauty of Bayesian analysis is that it allows us to build models hierarchically to incorporate all our knowledge about the structure of the data generation process, not just about the parameters. In practice, we often know quite a lot about how data might have been generated and that knowledge can make a dramatic difference in how precise our inference can be. The paper examines the use of Bayesian inference in statistical models that include a compositional process. It discusses the insights that may be obtained from this approach, including as examples: distinguishing between structural and censored zeros, examining the choice between compositional or multivariate covariates, identifying the number of end-members in a composition and identifying changepoints in compositional processes.
 
ISBN9788487867767
 
DC FieldValue
dc.contributor.authorBacon-Shone, J
 
dc.date.accessioned2011-08-26T15:05:53Z
 
dc.date.available2011-08-26T15:05:53Z
 
dc.date.issued2011
 
dc.description.abstractStatistical modeling in practice encompasses both the exploratory process, which is an inductive scientific approach and the confirmatory modeling process, which uses the deductive scientific approach. This paper will focus primarily on the confirmatory modeling process. As the great applied statistician George Box, has famously said “all models are wrong, but some are useful”. My version would be “all models are wrong, but some are essential for progress”! While John Aitchison has changed the world of compositional data analysis, the world of Bayesian statistics has also changed dramatically thanks to the Gibbs sampler, which allows Bayesian analysis of complex non-linear models and particularly random effects models. The beauty of Bayesian analysis is that it allows us to build models hierarchically to incorporate all our knowledge about the structure of the data generation process, not just about the parameters. In practice, we often know quite a lot about how data might have been generated and that knowledge can make a dramatic difference in how precise our inference can be. The paper examines the use of Bayesian inference in statistical models that include a compositional process. It discusses the insights that may be obtained from this approach, including as examples: distinguishing between structural and censored zeros, examining the choice between compositional or multivariate covariates, identifying the number of end-members in a composition and identifying changepoints in compositional processes.
 
dc.description.otherThe 4th International Workshop on Compositional Data Analysis (CoDaWork 2011), Girona, Spain, 9-13 May 2011. In Proceedings of the 4th CoDaWork, 2011
 
dc.identifier.citationThe 4th International Workshop on Compositional Data Analysis (CoDaWork 2011), Girona, Spain, 9-13 May 2011. In Proceedings of the 4th CoDaWork, 2011 [How to Cite?]
 
dc.identifier.hkuros191652
 
dc.identifier.isbn9788487867767
 
dc.identifier.openurl
 
dc.identifier.urihttp://hdl.handle.net/10722/138523
 
dc.languageeng
 
dc.relation.ispartofProceedings of the 4th International Workshop on Compositional Data Analysis
 
dc.titleCompositional data, Bayesian inference and the modeling process
 
dc.typeConference_Paper
 
<?xml encoding="utf-8" version="1.0"?>
<item><contributor.author>Bacon-Shone, J</contributor.author>
<date.accessioned>2011-08-26T15:05:53Z</date.accessioned>
<date.available>2011-08-26T15:05:53Z</date.available>
<date.issued>2011</date.issued>
<identifier.citation>The 4th International Workshop on Compositional Data Analysis (CoDaWork 2011), Girona, Spain, 9-13 May 2011. In Proceedings of the 4th CoDaWork, 2011</identifier.citation>
<identifier.isbn>9788487867767</identifier.isbn>
<identifier.uri>http://hdl.handle.net/10722/138523</identifier.uri>
<description.abstract>Statistical modeling in practice encompasses both the exploratory process, which is an inductive scientific approach and the confirmatory modeling process, which uses the deductive scientific approach. This paper will focus primarily on the confirmatory modeling process. As the great applied statistician George Box, has famously said &#8220;all models are wrong, but some are useful&#8221;. My version would be &#8220;all models are wrong, but some are essential for progress&#8221;! While John Aitchison has changed the world of compositional data analysis, the world of Bayesian statistics has also changed dramatically thanks to the Gibbs sampler, which allows Bayesian analysis of complex non-linear models and particularly random effects models. The beauty of Bayesian analysis is that it allows us to build models hierarchically to incorporate all our knowledge about the structure of the data generation process, not just about the parameters. In practice, we often know quite a lot about how data might have been generated and that knowledge can make a dramatic difference in how precise our inference can be. The paper examines the use of Bayesian inference in statistical models that include a compositional process. It discusses the insights that may be obtained from this approach, including as examples: distinguishing between structural and censored zeros, examining the choice between compositional or multivariate covariates, identifying the number of end-members in a composition and identifying changepoints in compositional processes.</description.abstract>
<language>eng</language>
<relation.ispartof>Proceedings of the 4th International Workshop on Compositional Data Analysis</relation.ispartof>
<title>Compositional data, Bayesian inference and the modeling process</title>
<type>Conference_Paper</type>
<identifier.openurl>http://library.hku.hk:4550/resserv?sid=HKU:IR&amp;issn=978-84-87867-76-7&amp;volume=&amp;spage=&amp;epage=&amp;date=2011&amp;atitle=Compositional+data,+Bayesian+inference+and+the+modeling+process</identifier.openurl>
<identifier.hkuros>191652</identifier.hkuros>
<description.other>The 4th International Workshop on Compositional Data Analysis (CoDaWork 2011), Girona, Spain, 9-13 May 2011. In Proceedings of the 4th CoDaWork, 2011</description.other>
</item>