Cargando…
Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables()
Multiple imputation is a popular way to handle missing data. Automated procedures are widely available in standard software. However, such automated procedures may hide many assumptions and possible difficulties from the view of the data analyst. Imputation procedures such as monotone imputation and...
Autores principales: | , , |
---|---|
Formato: | Online Artículo Texto |
Lenguaje: | English |
Publicado: |
North-Holland Pub. Co
2010
|
Materias: | |
Acceso en línea: | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3990447/ https://www.ncbi.nlm.nih.gov/pubmed/24748700 http://dx.doi.org/10.1016/j.csda.2010.04.005 |
_version_ | 1782312280835227648 |
---|---|
author | White, Ian R. Daniel, Rhian Royston, Patrick |
author_facet | White, Ian R. Daniel, Rhian Royston, Patrick |
author_sort | White, Ian R. |
collection | PubMed |
description | Multiple imputation is a popular way to handle missing data. Automated procedures are widely available in standard software. However, such automated procedures may hide many assumptions and possible difficulties from the view of the data analyst. Imputation procedures such as monotone imputation and imputation by chained equations often involve the fitting of a regression model for a categorical outcome. If perfect prediction occurs in such a model, then automated procedures may give severely biased results. This is a problem in some standard software, but it may be avoided by bootstrap methods, penalised regression methods, or a new augmentation procedure. |
format | Online Article Text |
id | pubmed-3990447 |
institution | National Center for Biotechnology Information |
language | English |
publishDate | 2010 |
publisher | North-Holland Pub. Co |
record_format | MEDLINE/PubMed |
spelling | pubmed-39904472014-04-18 Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() White, Ian R. Daniel, Rhian Royston, Patrick Comput Stat Data Anal Article Multiple imputation is a popular way to handle missing data. Automated procedures are widely available in standard software. However, such automated procedures may hide many assumptions and possible difficulties from the view of the data analyst. Imputation procedures such as monotone imputation and imputation by chained equations often involve the fitting of a regression model for a categorical outcome. If perfect prediction occurs in such a model, then automated procedures may give severely biased results. This is a problem in some standard software, but it may be avoided by bootstrap methods, penalised regression methods, or a new augmentation procedure. North-Holland Pub. Co 2010-10-01 /pmc/articles/PMC3990447/ /pubmed/24748700 http://dx.doi.org/10.1016/j.csda.2010.04.005 Text en © 2010 Elsevier B.V. https://creativecommons.org/licenses/by/4.0/ Open Access under CC BY 4.0 (https://creativecommons.org/licenses/by/4.0/) license |
spellingShingle | Article White, Ian R. Daniel, Rhian Royston, Patrick Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title | Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title_full | Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title_fullStr | Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title_full_unstemmed | Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title_short | Avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
title_sort | avoiding bias due to perfect prediction in multiple imputation of incomplete categorical variables() |
topic | Article |
url | https://www.ncbi.nlm.nih.gov/pmc/articles/PMC3990447/ https://www.ncbi.nlm.nih.gov/pubmed/24748700 http://dx.doi.org/10.1016/j.csda.2010.04.005 |
work_keys_str_mv | AT whiteianr avoidingbiasduetoperfectpredictioninmultipleimputationofincompletecategoricalvariables AT danielrhian avoidingbiasduetoperfectpredictioninmultipleimputationofincompletecategoricalvariables AT roystonpatrick avoidingbiasduetoperfectpredictioninmultipleimputationofincompletecategoricalvariables |