Penalized logistic regression with low prevalence exposures beyond high dimensional settings
| dc.rights.license | open | en_US |
| dc.contributor.author | DOERKEN, S. | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | AVALOS FERNANDEZ, Marta | |
| hal.structure.identifier | Bordeaux population health [BPH] | |
| dc.contributor.author | LAGARDE, Emmanuel | |
| dc.contributor.author | SCHUMACHER, M. | |
| dc.date.accessioned | 2020-06-05T10:41:54Z | |
| dc.date.available | 2020-06-05T10:41:54Z | |
| dc.date.issued | 2019-05-21 | |
| dc.identifier.issn | 1932-6203 | en_US |
| dc.identifier.uri | https://oskar-bordeaux.fr/handle/20.500.12278/7769 | |
| dc.description.abstractEn | Estimating and selecting risk factors with extremely low prevalences of exposure for a binary outcome is a challenge because classical standard techniques, markedly logistic regression, often fail to provide meaningful results in such settings. While penalized regression methods are widely used in high-dimensional settings, we were able to show their usefulness in low-dimensional settings as well. Specifically, we demonstrate that Firth correction, ridge, the lasso and boosting all improve the estimation for low-prevalence risk factors. While the methods themselves are well-established, comparison studies are needed to assess their potential benefits in this context. This is done here using the dataset of a large unmatched case-control study from France (2005-2008) about the relationship between prescription medicines and road traffic accidents and an accompanying simulation study. Results show that the estimation of risk factors with prevalences below 0.1% can be drastically improved by using Firth correction and boosting in particular, especially for ultra-low prevalences. When a moderate number of low prevalence exposures is available, we recommend the use of penalized techniques. | |
| dc.language.iso | EN | en_US |
| dc.rights | Attribution 4.0 International (CC BY 4.0) | |
| dc.rights.uri | https://creativecommons.org/licenses/by/4.0/ | |
| dc.subject.en | SISTM | |
| dc.subject.en | IETO | |
| dc.title.en | Penalized logistic regression with low prevalence exposures beyond high dimensional settings | |
| dc.title.alternative | PLoS One | en_US |
| dc.type | Article de revue | en_US |
| dc.identifier.doi | 10.1371/journal.pone.0217057 | en_US |
| dc.subject.hal | Sciences du Vivant [q-bio]/Santé publique et épidémiologie | en_US |
| dc.identifier.pubmed | 31107924 | en_US |
| bordeaux.journal | PLoS ONE | en_US |
| bordeaux.page | e0217057 | en_US |
| bordeaux.volume | 14 | en_US |
| bordeaux.hal.laboratories | Bordeaux Population Health Research Center (BPH) - U1219 | en_US |
| bordeaux.issue | 5 | en_US |
| bordeaux.institution | Université de Bordeaux | en_US |
| bordeaux.team | SISTM_BPH | |
| bordeaux.peerReviewed | oui | en_US |
| bordeaux.inpress | non | en_US |
| hal.export | false | |
| bordeaux.COinS | ctx_ver=Z39.88-2004&rft_val_fmt=info:ofi/fmt:kev:mtx:journal&rft.jtitle=PLoS%20ONE&rft.date=2019-05-21&rft.volume=14&rft.issue=5&rft.spage=e0217057&rft.epage=e0217057&rft.eissn=1932-6203&rft.issn=1932-6203&rft.au=DOERKEN,%20S.&AVALOS%20FERNANDEZ,%20Marta&LAGARDE,%20Emmanuel&SCHUMACHER,%20M.&rft.genre=article |
