Operational Bayesian GLS regression for regional hydrologic analyses
Autor(a) principal: | |
---|---|
Data de Publicação: | 2020 |
Outros Autores: | , , , |
Tipo de documento: | Artigo |
Idioma: | eng |
Título da fonte: | Repositório Institucional da Universidade Federal do Ceará (UFC) |
Texto Completo: | http://www.repositorio.ufc.br/handle/riufc/59253 |
Resumo: | This paper develops the quasi analytic Bayesian analysis of the generalized least squares (GLS)(BGLS) model introduced by Reis et al. (2005, https://doi.org/10.1029/2004WR003445) into an operationaland statistically comprehensive GLS regional hydrologic regression methodology to estimate oodquantiles, regional shape parameters, low ows, and other statistics with spatially correlated ow records.New GLS regression diagnostic statistics include a Bayesian plausibility value, pseudo adjusted R2,pseudo analysis of variance table, and two diagnostic error variance ratios. Traditional leverage andinuence are extended to identify rogue observations, address lack of t, and support gauge network designand regionofinuence regression. Formulas are derived for the Bayesian computation of estimators,standard errors, and diagnostic statistics. The use of BGLS and the new diagnostic statistics are illustratedwith a regional logspace skew regression analysis for the Piedmont region in the Southeastern U.S. Acomparison of ordinary, weighted, and GLS analyses documents the advantages of the Bayesian estimatorover the method ofmoment estimator of model error variance introduced by Stedinger and Tasker (1985,https://doi.org/10.1029/WR021i009p01421). Of the three types of analyses, only GLS considers thecovariance among concurrent ows. The example demonstrates that GLS regional skewness models can behighly accurate when correctly analyzed: The BGLS average variance of prediction is 0.090 for SouthCarolina (92 stations), whereas a traditional ordinary least squares analysis published by the U.S.Geological Survey yielded 0.193 (Feaster & Tasker, 2002, https://doi.org/10.3133/wri024140). BGLSprovides a statistical valid framework for the rigorous analysis of spatially correlated hydrologic data,allowing for the estimation of parameters and their actual precision and computation of several diagnosticstatistics, as well as correctly attributing variability to the three key sources: time sampling error, modelerror, and signal |
id |
UFC-7_1763bfcb908bf36da5e52157a443255b |
---|---|
oai_identifier_str |
oai:repositorio.ufc.br:riufc/59253 |
network_acronym_str |
UFC-7 |
network_name_str |
Repositório Institucional da Universidade Federal do Ceará (UFC) |
repository_id_str |
|
spelling |
Operational Bayesian GLS regression for regional hydrologic analysesOperational Bayesian GLS regression for regional hydrologic analysesHidrologiaÁguaPesquisaThis paper develops the quasi analytic Bayesian analysis of the generalized least squares (GLS)(BGLS) model introduced by Reis et al. (2005, https://doi.org/10.1029/2004WR003445) into an operationaland statistically comprehensive GLS regional hydrologic regression methodology to estimate oodquantiles, regional shape parameters, low ows, and other statistics with spatially correlated ow records.New GLS regression diagnostic statistics include a Bayesian plausibility value, pseudo adjusted R2,pseudo analysis of variance table, and two diagnostic error variance ratios. Traditional leverage andinuence are extended to identify rogue observations, address lack of t, and support gauge network designand regionofinuence regression. Formulas are derived for the Bayesian computation of estimators,standard errors, and diagnostic statistics. The use of BGLS and the new diagnostic statistics are illustratedwith a regional logspace skew regression analysis for the Piedmont region in the Southeastern U.S. Acomparison of ordinary, weighted, and GLS analyses documents the advantages of the Bayesian estimatorover the method ofmoment estimator of model error variance introduced by Stedinger and Tasker (1985,https://doi.org/10.1029/WR021i009p01421). Of the three types of analyses, only GLS considers thecovariance among concurrent ows. The example demonstrates that GLS regional skewness models can behighly accurate when correctly analyzed: The BGLS average variance of prediction is 0.090 for SouthCarolina (92 stations), whereas a traditional ordinary least squares analysis published by the U.S.Geological Survey yielded 0.193 (Feaster & Tasker, 2002, https://doi.org/10.3133/wri024140). BGLSprovides a statistical valid framework for the rigorous analysis of spatially correlated hydrologic data,allowing for the estimation of parameters and their actual precision and computation of several diagnosticstatistics, as well as correctly attributing variability to the three key sources: time sampling error, modelerror, and signalWater Resources Research2021-06-29T12:33:21Z2021-06-29T12:33:21Z2020info:eu-repo/semantics/publishedVersioninfo:eu-repo/semantics/articleapplication/pdfREIS JÚNIOR, Direceu S.; VEILLEUX, Andrea G.; LAMONTAGNE, Jonathan R.; STEDINGER, Jery R.; MARTINS, Eduardo Sávio Passos Rodrigues. Operational Bayesian GLS regression for regional hydrologic analyses. Water Resources Research, United States, v. 56, p. 1-35, 2020.1944-7973http://www.repositorio.ufc.br/handle/riufc/59253Reis Júnior, Dirceu S.Veilleux, Andrea G.Lamontagn, Jonathan R.Stedinger, Jery R.Martins, Eduardo Sávio Passos Rodriguesengreponame:Repositório Institucional da Universidade Federal do Ceará (UFC)instname:Universidade Federal do Ceará (UFC)instacron:UFCinfo:eu-repo/semantics/openAccess2022-11-29T12:25:20Zoai:repositorio.ufc.br:riufc/59253Repositório InstitucionalPUBhttp://www.repositorio.ufc.br/ri-oai/requestbu@ufc.br || repositorio@ufc.bropendoar:2024-09-11T18:22:26.251965Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC)false |
dc.title.none.fl_str_mv |
Operational Bayesian GLS regression for regional hydrologic analyses Operational Bayesian GLS regression for regional hydrologic analyses |
title |
Operational Bayesian GLS regression for regional hydrologic analyses |
spellingShingle |
Operational Bayesian GLS regression for regional hydrologic analyses Reis Júnior, Dirceu S. Hidrologia Água Pesquisa |
title_short |
Operational Bayesian GLS regression for regional hydrologic analyses |
title_full |
Operational Bayesian GLS regression for regional hydrologic analyses |
title_fullStr |
Operational Bayesian GLS regression for regional hydrologic analyses |
title_full_unstemmed |
Operational Bayesian GLS regression for regional hydrologic analyses |
title_sort |
Operational Bayesian GLS regression for regional hydrologic analyses |
author |
Reis Júnior, Dirceu S. |
author_facet |
Reis Júnior, Dirceu S. Veilleux, Andrea G. Lamontagn, Jonathan R. Stedinger, Jery R. Martins, Eduardo Sávio Passos Rodrigues |
author_role |
author |
author2 |
Veilleux, Andrea G. Lamontagn, Jonathan R. Stedinger, Jery R. Martins, Eduardo Sávio Passos Rodrigues |
author2_role |
author author author author |
dc.contributor.author.fl_str_mv |
Reis Júnior, Dirceu S. Veilleux, Andrea G. Lamontagn, Jonathan R. Stedinger, Jery R. Martins, Eduardo Sávio Passos Rodrigues |
dc.subject.por.fl_str_mv |
Hidrologia Água Pesquisa |
topic |
Hidrologia Água Pesquisa |
description |
This paper develops the quasi analytic Bayesian analysis of the generalized least squares (GLS)(BGLS) model introduced by Reis et al. (2005, https://doi.org/10.1029/2004WR003445) into an operationaland statistically comprehensive GLS regional hydrologic regression methodology to estimate oodquantiles, regional shape parameters, low ows, and other statistics with spatially correlated ow records.New GLS regression diagnostic statistics include a Bayesian plausibility value, pseudo adjusted R2,pseudo analysis of variance table, and two diagnostic error variance ratios. Traditional leverage andinuence are extended to identify rogue observations, address lack of t, and support gauge network designand regionofinuence regression. Formulas are derived for the Bayesian computation of estimators,standard errors, and diagnostic statistics. The use of BGLS and the new diagnostic statistics are illustratedwith a regional logspace skew regression analysis for the Piedmont region in the Southeastern U.S. Acomparison of ordinary, weighted, and GLS analyses documents the advantages of the Bayesian estimatorover the method ofmoment estimator of model error variance introduced by Stedinger and Tasker (1985,https://doi.org/10.1029/WR021i009p01421). Of the three types of analyses, only GLS considers thecovariance among concurrent ows. The example demonstrates that GLS regional skewness models can behighly accurate when correctly analyzed: The BGLS average variance of prediction is 0.090 for SouthCarolina (92 stations), whereas a traditional ordinary least squares analysis published by the U.S.Geological Survey yielded 0.193 (Feaster & Tasker, 2002, https://doi.org/10.3133/wri024140). BGLSprovides a statistical valid framework for the rigorous analysis of spatially correlated hydrologic data,allowing for the estimation of parameters and their actual precision and computation of several diagnosticstatistics, as well as correctly attributing variability to the three key sources: time sampling error, modelerror, and signal |
publishDate |
2020 |
dc.date.none.fl_str_mv |
2020 2021-06-29T12:33:21Z 2021-06-29T12:33:21Z |
dc.type.status.fl_str_mv |
info:eu-repo/semantics/publishedVersion |
dc.type.driver.fl_str_mv |
info:eu-repo/semantics/article |
format |
article |
status_str |
publishedVersion |
dc.identifier.uri.fl_str_mv |
REIS JÚNIOR, Direceu S.; VEILLEUX, Andrea G.; LAMONTAGNE, Jonathan R.; STEDINGER, Jery R.; MARTINS, Eduardo Sávio Passos Rodrigues. Operational Bayesian GLS regression for regional hydrologic analyses. Water Resources Research, United States, v. 56, p. 1-35, 2020. 1944-7973 http://www.repositorio.ufc.br/handle/riufc/59253 |
identifier_str_mv |
REIS JÚNIOR, Direceu S.; VEILLEUX, Andrea G.; LAMONTAGNE, Jonathan R.; STEDINGER, Jery R.; MARTINS, Eduardo Sávio Passos Rodrigues. Operational Bayesian GLS regression for regional hydrologic analyses. Water Resources Research, United States, v. 56, p. 1-35, 2020. 1944-7973 |
url |
http://www.repositorio.ufc.br/handle/riufc/59253 |
dc.language.iso.fl_str_mv |
eng |
language |
eng |
dc.rights.driver.fl_str_mv |
info:eu-repo/semantics/openAccess |
eu_rights_str_mv |
openAccess |
dc.format.none.fl_str_mv |
application/pdf |
dc.publisher.none.fl_str_mv |
Water Resources Research |
publisher.none.fl_str_mv |
Water Resources Research |
dc.source.none.fl_str_mv |
reponame:Repositório Institucional da Universidade Federal do Ceará (UFC) instname:Universidade Federal do Ceará (UFC) instacron:UFC |
instname_str |
Universidade Federal do Ceará (UFC) |
instacron_str |
UFC |
institution |
UFC |
reponame_str |
Repositório Institucional da Universidade Federal do Ceará (UFC) |
collection |
Repositório Institucional da Universidade Federal do Ceará (UFC) |
repository.name.fl_str_mv |
Repositório Institucional da Universidade Federal do Ceará (UFC) - Universidade Federal do Ceará (UFC) |
repository.mail.fl_str_mv |
bu@ufc.br || repositorio@ufc.br |
_version_ |
1813028776745893888 |