Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure
Udgivelsesdato: 2007-Jan PURPOSE: The purpose of the study is to compare different approaches to the identification of confounders needed for analyzing observational data. Whereas standard analysis usually is conducted as if the confounders were known a priori, selection uncertainty also must be tak...
Published in: | Annals of Epidemiology |
---|---|
Main Authors: | , , , |
Format: | Article in Journal/Newspaper |
Language: | English |
Published: |
2006
|
Subjects: | |
Online Access: | https://curis.ku.dk/portal/da/publications/confounder-selection-in-environmental-epidemiology-assessment-of-health-effects-of-prenatal-mercury-exposure(6de920b0-9ea9-11de-bc73-000ea68e967b).html https://doi.org/10.1016/j.annepidem.2006.05.007 |
id |
ftcopenhagenunip:oai:pure.atira.dk:publications/6de920b0-9ea9-11de-bc73-000ea68e967b |
---|---|
record_format |
openpolar |
spelling |
ftcopenhagenunip:oai:pure.atira.dk:publications/6de920b0-9ea9-11de-bc73-000ea68e967b 2024-04-21T08:01:50+00:00 Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure Budtz-Jørgensen, Esben Keiding, Niels Grandjean, Philippe Weihe, Pal 2006 https://curis.ku.dk/portal/da/publications/confounder-selection-in-environmental-epidemiology-assessment-of-health-effects-of-prenatal-mercury-exposure(6de920b0-9ea9-11de-bc73-000ea68e967b).html https://doi.org/10.1016/j.annepidem.2006.05.007 eng eng info:eu-repo/semantics/restrictedAccess Budtz-Jørgensen , E , Keiding , N , Grandjean , P & Weihe , P 2006 , ' Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure ' , Annals of Epidemiology , vol. 17 , no. 1 , pp. 27-35 . https://doi.org/10.1016/j.annepidem.2006.05.007 article 2006 ftcopenhagenunip https://doi.org/10.1016/j.annepidem.2006.05.007 2024-03-28T01:21:41Z Udgivelsesdato: 2007-Jan PURPOSE: The purpose of the study is to compare different approaches to the identification of confounders needed for analyzing observational data. Whereas standard analysis usually is conducted as if the confounders were known a priori, selection uncertainty also must be taken into account. METHODS: Confounders were selected by using backward elimination (BE), change in estimate (CIE) method, Akaike information criterion, Bayesian information criterion (BIC), and an empirical approach using a priori information. A modified ridge regression estimator, which shrinks effects of confounders toward zero, also was considered. For each criterion, uncertainty in the estimated exposure effect was assessed by using bootstrap simulations for which confounders were selected in each sample. These methods were illustrated by using data for mercury neurotoxicity in Faroe Islands children. Point estimates and standard errors of mercury effects on confounder-sensitive neurobehavioral outcomes were calculated for each selection procedure. RESULTS: The full model and the empirical a priori model showed approximately the same precision, and these methods were (slightly) inferior to only modified ridge regression. Lower precisions were obtained by using BE with a low cutoff level, BIC, and CIE. CONCLUSIONS: Standard analysis ignores model selection uncertainty and is likely to yield overoptimistic inferences. Thus, the traditional BE procedure with p = 5% should be avoided. If data-dependent procedures are required for confounder identification, we recommend that inferences be based on bootstrap statistics to describe the selection process. Article in Journal/Newspaper Faroe Islands University of Copenhagen: Research Annals of Epidemiology 17 1 27 35 |
institution |
Open Polar |
collection |
University of Copenhagen: Research |
op_collection_id |
ftcopenhagenunip |
language |
English |
description |
Udgivelsesdato: 2007-Jan PURPOSE: The purpose of the study is to compare different approaches to the identification of confounders needed for analyzing observational data. Whereas standard analysis usually is conducted as if the confounders were known a priori, selection uncertainty also must be taken into account. METHODS: Confounders were selected by using backward elimination (BE), change in estimate (CIE) method, Akaike information criterion, Bayesian information criterion (BIC), and an empirical approach using a priori information. A modified ridge regression estimator, which shrinks effects of confounders toward zero, also was considered. For each criterion, uncertainty in the estimated exposure effect was assessed by using bootstrap simulations for which confounders were selected in each sample. These methods were illustrated by using data for mercury neurotoxicity in Faroe Islands children. Point estimates and standard errors of mercury effects on confounder-sensitive neurobehavioral outcomes were calculated for each selection procedure. RESULTS: The full model and the empirical a priori model showed approximately the same precision, and these methods were (slightly) inferior to only modified ridge regression. Lower precisions were obtained by using BE with a low cutoff level, BIC, and CIE. CONCLUSIONS: Standard analysis ignores model selection uncertainty and is likely to yield overoptimistic inferences. Thus, the traditional BE procedure with p = 5% should be avoided. If data-dependent procedures are required for confounder identification, we recommend that inferences be based on bootstrap statistics to describe the selection process. |
format |
Article in Journal/Newspaper |
author |
Budtz-Jørgensen, Esben Keiding, Niels Grandjean, Philippe Weihe, Pal |
spellingShingle |
Budtz-Jørgensen, Esben Keiding, Niels Grandjean, Philippe Weihe, Pal Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
author_facet |
Budtz-Jørgensen, Esben Keiding, Niels Grandjean, Philippe Weihe, Pal |
author_sort |
Budtz-Jørgensen, Esben |
title |
Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
title_short |
Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
title_full |
Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
title_fullStr |
Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
title_full_unstemmed |
Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
title_sort |
confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure |
publishDate |
2006 |
url |
https://curis.ku.dk/portal/da/publications/confounder-selection-in-environmental-epidemiology-assessment-of-health-effects-of-prenatal-mercury-exposure(6de920b0-9ea9-11de-bc73-000ea68e967b).html https://doi.org/10.1016/j.annepidem.2006.05.007 |
genre |
Faroe Islands |
genre_facet |
Faroe Islands |
op_source |
Budtz-Jørgensen , E , Keiding , N , Grandjean , P & Weihe , P 2006 , ' Confounder selection in environmental epidemiology: assessment of health effects of prenatal mercury exposure ' , Annals of Epidemiology , vol. 17 , no. 1 , pp. 27-35 . https://doi.org/10.1016/j.annepidem.2006.05.007 |
op_rights |
info:eu-repo/semantics/restrictedAccess |
op_doi |
https://doi.org/10.1016/j.annepidem.2006.05.007 |
container_title |
Annals of Epidemiology |
container_volume |
17 |
container_issue |
1 |
container_start_page |
27 |
op_container_end_page |
35 |
_version_ |
1796941931277713408 |