Homoscedasticity: an overlooked critical assumption for linear regression

Linear regression is widely used in biomedical and psychosocial research. A critical assumption that is often overlooked is homoscedasticity. Unlike normality, the other assumption on data distribution, homoscedasticity is often taken for granted when fitting linear regression models. However, contr...

Descripción completa

Detalles Bibliográficos
Autores principales: Yang, Kun, Tu, Justin, Chen, Tian
Formato: Online Artículo Texto
Lenguaje:English
Publicado: BMJ Publishing Group 2019
Materias:
Biostatistical Methods in Psychiatry
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6802968/
https://www.ncbi.nlm.nih.gov/pubmed/31673679
http://dx.doi.org/10.1136/gpsych-2019-100148
_version_ 1783460884316684288
author Yang, Kun
Tu, Justin
Chen, Tian
author_facet Yang, Kun
Tu, Justin
Chen, Tian
author_sort Yang, Kun
collection PubMed
description Linear regression is widely used in biomedical and psychosocial research. A critical assumption that is often overlooked is homoscedasticity. Unlike normality, the other assumption on data distribution, homoscedasticity is often taken for granted when fitting linear regression models. However, contrary to popular belief, this assumption actually has a bigger impact on validity of linear regression results than normality. In this report, we use Monte Carlo simulation studies to investigate and compare their effects on validity of inference.
format Online
Article
Text
id pubmed-6802968
institution National Center for Biotechnology Information
language English
publishDate 2019
publisher BMJ Publishing Group
record_format MEDLINE/PubMed
spelling pubmed-68029682019-10-31 Homoscedasticity: an overlooked critical assumption for linear regression Yang, Kun Tu, Justin Chen, Tian Gen Psychiatr Biostatistical Methods in Psychiatry Linear regression is widely used in biomedical and psychosocial research. A critical assumption that is often overlooked is homoscedasticity. Unlike normality, the other assumption on data distribution, homoscedasticity is often taken for granted when fitting linear regression models. However, contrary to popular belief, this assumption actually has a bigger impact on validity of linear regression results than normality. In this report, we use Monte Carlo simulation studies to investigate and compare their effects on validity of inference. BMJ Publishing Group 2019-10-17 /pmc/articles/PMC6802968/ /pubmed/31673679 http://dx.doi.org/10.1136/gpsych-2019-100148 Text en © Author(s) (or their employer(s)) 2019. Re-use permitted under CC BY-NC. No commercial re-use. See rights and permissions. Published by BMJ. This is an open access article distributed in accordance with the Creative Commons Attribution Non Commercial (CC BY-NC 4.0) license, which permits others to distribute, remix, adapt, build upon this work non-commercially, and license their derivative works on different terms, provided the original work is properly cited, appropriate credit is given, any changes made indicated, and the use is non-commercial. See: http://creativecommons.org/licenses/by-nc/4.0/.
spellingShingle Biostatistical Methods in Psychiatry
Yang, Kun
Tu, Justin
Chen, Tian
Homoscedasticity: an overlooked critical assumption for linear regression
title Homoscedasticity: an overlooked critical assumption for linear regression
title_full Homoscedasticity: an overlooked critical assumption for linear regression
title_fullStr Homoscedasticity: an overlooked critical assumption for linear regression
title_full_unstemmed Homoscedasticity: an overlooked critical assumption for linear regression
title_short Homoscedasticity: an overlooked critical assumption for linear regression
title_sort homoscedasticity: an overlooked critical assumption for linear regression
topic Biostatistical Methods in Psychiatry
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC6802968/
https://www.ncbi.nlm.nih.gov/pubmed/31673679
http://dx.doi.org/10.1136/gpsych-2019-100148
work_keys_str_mv AT yangkun homoscedasticityanoverlookedcriticalassumptionforlinearregression
AT tujustin homoscedasticityanoverlookedcriticalassumptionforlinearregression
AT chentian homoscedasticityanoverlookedcriticalassumptionforlinearregression

Ejemplares similares