Cargando…

A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects

Variation in the odds ratio (OR) resulting from selection of cutoffs for categorizing continuous variables is rarely discussed. We present results for the effect of varying cutoffs used to categorize a mismeasured exposure in a simulated population in the context of autism spectrum disorders researc...

Descripción completa

Detalles Bibliográficos
Autores principales: Heavner, Karyn, Burstyn, Igor
Formato: Online Artículo Texto
Lenguaje:English
Publicado: MDPI 2015
Materias:
Acceso en línea:https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4555337/
https://www.ncbi.nlm.nih.gov/pubmed/26305250
http://dx.doi.org/10.3390/ijerph120810198
_version_ 1782388183176052736
author Heavner, Karyn
Burstyn, Igor
author_facet Heavner, Karyn
Burstyn, Igor
author_sort Heavner, Karyn
collection PubMed
description Variation in the odds ratio (OR) resulting from selection of cutoffs for categorizing continuous variables is rarely discussed. We present results for the effect of varying cutoffs used to categorize a mismeasured exposure in a simulated population in the context of autism spectrum disorders research. Simulated cohorts were created with three distinct exposure-outcome curves and three measurement error variances for the exposure. ORs were calculated using logistic regression for 61 cutoffs (mean ± 3 standard deviations) used to dichotomize the observed exposure. ORs were calculated for five categories with a wide range for the cutoffs. For each scenario and cutoff, the OR, sensitivity, and specificity were calculated. The three exposure-outcome relationships had distinctly shaped OR (versus cutoff) curves, but increasing measurement error obscured the shape. At extreme cutoffs, there was non-monotonic oscillation in the ORs that cannot be attributed to “small numbers.” Exposure misclassification following categorization of the mismeasured exposure was differential, as predicted by theory. Sensitivity was higher among cases and specificity among controls. Cutoffs chosen for categorizing continuous variables can have profound effects on study results. When measurement error is not too great, the shape of the OR curve may provide insight into the true shape of the exposure-disease relationship.
format Online
Article
Text
id pubmed-4555337
institution National Center for Biotechnology Information
language English
publishDate 2015
publisher MDPI
record_format MEDLINE/PubMed
spelling pubmed-45553372015-09-01 A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects Heavner, Karyn Burstyn, Igor Int J Environ Res Public Health Article Variation in the odds ratio (OR) resulting from selection of cutoffs for categorizing continuous variables is rarely discussed. We present results for the effect of varying cutoffs used to categorize a mismeasured exposure in a simulated population in the context of autism spectrum disorders research. Simulated cohorts were created with three distinct exposure-outcome curves and three measurement error variances for the exposure. ORs were calculated using logistic regression for 61 cutoffs (mean ± 3 standard deviations) used to dichotomize the observed exposure. ORs were calculated for five categories with a wide range for the cutoffs. For each scenario and cutoff, the OR, sensitivity, and specificity were calculated. The three exposure-outcome relationships had distinctly shaped OR (versus cutoff) curves, but increasing measurement error obscured the shape. At extreme cutoffs, there was non-monotonic oscillation in the ORs that cannot be attributed to “small numbers.” Exposure misclassification following categorization of the mismeasured exposure was differential, as predicted by theory. Sensitivity was higher among cases and specificity among controls. Cutoffs chosen for categorizing continuous variables can have profound effects on study results. When measurement error is not too great, the shape of the OR curve may provide insight into the true shape of the exposure-disease relationship. MDPI 2015-08-24 2015-08 /pmc/articles/PMC4555337/ /pubmed/26305250 http://dx.doi.org/10.3390/ijerph120810198 Text en © 2015 by the authors; licensee MDPI, Basel, Switzerland. This article is an open access article distributed under the terms and conditions of the Creative Commons Attribution license (http://creativecommons.org/licenses/by/4.0/).
spellingShingle Article
Heavner, Karyn
Burstyn, Igor
A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title_full A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title_fullStr A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title_full_unstemmed A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title_short A Simulation Study of Categorizing Continuous Exposure Variables Measured with Error in Autism Research: Small Changes with Large Effects
title_sort simulation study of categorizing continuous exposure variables measured with error in autism research: small changes with large effects
topic Article
url https://www.ncbi.nlm.nih.gov/pmc/articles/PMC4555337/
https://www.ncbi.nlm.nih.gov/pubmed/26305250
http://dx.doi.org/10.3390/ijerph120810198
work_keys_str_mv AT heavnerkaryn asimulationstudyofcategorizingcontinuousexposurevariablesmeasuredwitherrorinautismresearchsmallchangeswithlargeeffects
AT burstynigor asimulationstudyofcategorizingcontinuousexposurevariablesmeasuredwitherrorinautismresearchsmallchangeswithlargeeffects
AT heavnerkaryn simulationstudyofcategorizingcontinuousexposurevariablesmeasuredwitherrorinautismresearchsmallchangeswithlargeeffects
AT burstynigor simulationstudyofcategorizingcontinuousexposurevariablesmeasuredwitherrorinautismresearchsmallchangeswithlargeeffects