Correlation analysis for proportions via updating and resampling
Compositional data arise frequently in practice, but their statistical analysis is not yet well developed. Compositions arise when nonnegative random vectors are mapped into the unit simplex via a closure operation, e.g., when the amounts of certain minerals in a soil sample are converted to percent...
Main Authors: | , |
---|---|
Other Authors: | , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
country:IN
2010
|
Subjects: | |
Online Access: | http://hdl.handle.net/10281/22150 |
id |
ftunivmilanobic:oai:boa.unimib.it:10281/22150 |
---|---|
record_format |
openpolar |
spelling |
ftunivmilanobic:oai:boa.unimib.it:10281/22150 2023-11-12T04:20:26+01:00 Correlation analysis for proportions via updating and resampling MONTI, GIANNA SERAFINA Walther, G. Monti, G Walther, G 2010-03-30 http://hdl.handle.net/10281/22150 eng eng country:IN volume:3 issue:1 firstpage:17 lastpage:26 journal:JOURNAL OF STATISTICS: ADVANCES IN THEORY AND APPLICATIONS http://hdl.handle.net/10281/22150 compositional data bootstrap SECS-S/01 - STATISTICA info:eu-repo/semantics/article 2010 ftunivmilanobic 2023-10-17T22:18:23Z Compositional data arise frequently in practice, but their statistical analysis is not yet well developed. Compositions arise when nonnegative random vectors are mapped into the unit simplex via a closure operation, e.g., when the amounts of certain minerals in a soil sample are converted to percentages. Components in random compositions can never be stochastically independent, due to the spurious correlation introduced by taking the closure of the basis vectors. This paper aims to assess independence of the unobserved basis vectors based on the observed composition. We propose a resampling procedure that is based on an updating formula. A simulation study shows that this procedure works well in the case, where the components of the composition are roughly of the same size. We apply the procedure to a geochemical data set obtained from the Kola peninsula. Article in Journal/Newspaper kola peninsula Università degli Studi di Milano-Bicocca: BOA (Bicocca Open Archive) Kola Peninsula |
institution |
Open Polar |
collection |
Università degli Studi di Milano-Bicocca: BOA (Bicocca Open Archive) |
op_collection_id |
ftunivmilanobic |
language |
English |
topic |
compositional data bootstrap SECS-S/01 - STATISTICA |
spellingShingle |
compositional data bootstrap SECS-S/01 - STATISTICA MONTI, GIANNA SERAFINA Walther, G. Correlation analysis for proportions via updating and resampling |
topic_facet |
compositional data bootstrap SECS-S/01 - STATISTICA |
description |
Compositional data arise frequently in practice, but their statistical analysis is not yet well developed. Compositions arise when nonnegative random vectors are mapped into the unit simplex via a closure operation, e.g., when the amounts of certain minerals in a soil sample are converted to percentages. Components in random compositions can never be stochastically independent, due to the spurious correlation introduced by taking the closure of the basis vectors. This paper aims to assess independence of the unobserved basis vectors based on the observed composition. We propose a resampling procedure that is based on an updating formula. A simulation study shows that this procedure works well in the case, where the components of the composition are roughly of the same size. We apply the procedure to a geochemical data set obtained from the Kola peninsula. |
author2 |
Monti, G Walther, G |
format |
Article in Journal/Newspaper |
author |
MONTI, GIANNA SERAFINA Walther, G. |
author_facet |
MONTI, GIANNA SERAFINA Walther, G. |
author_sort |
MONTI, GIANNA SERAFINA |
title |
Correlation analysis for proportions via updating and resampling |
title_short |
Correlation analysis for proportions via updating and resampling |
title_full |
Correlation analysis for proportions via updating and resampling |
title_fullStr |
Correlation analysis for proportions via updating and resampling |
title_full_unstemmed |
Correlation analysis for proportions via updating and resampling |
title_sort |
correlation analysis for proportions via updating and resampling |
publisher |
country:IN |
publishDate |
2010 |
url |
http://hdl.handle.net/10281/22150 |
geographic |
Kola Peninsula |
geographic_facet |
Kola Peninsula |
genre |
kola peninsula |
genre_facet |
kola peninsula |
op_relation |
volume:3 issue:1 firstpage:17 lastpage:26 journal:JOURNAL OF STATISTICS: ADVANCES IN THEORY AND APPLICATIONS http://hdl.handle.net/10281/22150 |
_version_ |
1782336391159480320 |