Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance

Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance

We compared six methods for regression on log-normal heteroscedastic data with respect to the estimated associations with explanatory factors (bias and standard error) and the estimated expected outcome (bias and confidence interval). Method comparisons were based on results from a simulation study,...

Full description

Bibliographic Details
Main Authors: Sara Gustavsson, Björn Fagerberg, Gerd Sallsten, Eva M. Andersson
Format: Article
Language:English
Published: MDPI AG 2014-03-01
Series:International Journal of Environmental Research and Public Health
Subjects:
linear regression model
log-normal distribution
heteroscedasticity
biomarkers of inflammation
insulin resistance
simulation study
Online Access:http://www.mdpi.com/1660-4601/11/4/3521
id doaj-9359a11f33ed40968527aac286c77845
record_format Article
spelling doaj-9359a11f33ed40968527aac286c778452020-11-24T23:54:46ZengMDPI AGInternational Journal of Environmental Research and Public Health1660-46012014-03-011143521353910.3390/ijerph110403521ijerph110403521Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin ResistanceSara Gustavsson0Björn Fagerberg1Gerd Sallsten2Eva M. Andersson3Occupational and Environmental Medicine, Sahlgrenska University Hospital and Academy, University Of Gothenburg, Gothenburg SE-405 30, SwedenWallenberg Laboratory, Sahlgrenska Center for Cardiovascular and Metabolic Research, Sahlgrenska University Hospital, Gothenburg SE-413 45, SwedenOccupational and Environmental Medicine, Sahlgrenska University Hospital and Academy, University Of Gothenburg, Gothenburg SE-405 30, SwedenOccupational and Environmental Medicine, Sahlgrenska University Hospital and Academy, University Of Gothenburg, Gothenburg SE-405 30, SwedenWe compared six methods for regression on log-normal heteroscedastic data with respect to the estimated associations with explanatory factors (bias and standard error) and the estimated expected outcome (bias and confidence interval). Method comparisons were based on results from a simulation study, and also the estimation of the association between abdominal adiposity and two biomarkers; C-Reactive Protein (CRP) (inflammation marker,) and Insulin Resistance (HOMA-IR) (marker of insulin resistance). Five of the methods provide unbiased estimates of the associations and the expected outcome; two of them provide confidence intervals with correct coverage.http://www.mdpi.com/1660-4601/11/4/3521linear regression modellog-normal distributionheteroscedasticitybiomarkers of inflammationinsulin resistancesimulation study
collection DOAJ
language English
format Article
sources DOAJ
author Sara Gustavsson
Björn Fagerberg
Gerd Sallsten
Eva M. Andersson
spellingShingle Sara Gustavsson
Björn Fagerberg
Gerd Sallsten
Eva M. Andersson
Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
International Journal of Environmental Research and Public Health
linear regression model
log-normal distribution
heteroscedasticity
biomarkers of inflammation
insulin resistance
simulation study
author_facet Sara Gustavsson
Björn Fagerberg
Gerd Sallsten
Eva M. Andersson
author_sort Sara Gustavsson
title Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
title_short Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
title_full Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
title_fullStr Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
title_full_unstemmed Regression Models for Log-Normal Data: Comparing Different Methods for Quantifying the Association between Abdominal Adiposity and Biomarkers of Inflammation and Insulin Resistance
title_sort regression models for log-normal data: comparing different methods for quantifying the association between abdominal adiposity and biomarkers of inflammation and insulin resistance
publisher MDPI AG
series International Journal of Environmental Research and Public Health
issn 1660-4601
publishDate 2014-03-01
description We compared six methods for regression on log-normal heteroscedastic data with respect to the estimated associations with explanatory factors (bias and standard error) and the estimated expected outcome (bias and confidence interval). Method comparisons were based on results from a simulation study, and also the estimation of the association between abdominal adiposity and two biomarkers; C-Reactive Protein (CRP) (inflammation marker,) and Insulin Resistance (HOMA-IR) (marker of insulin resistance). Five of the methods provide unbiased estimates of the associations and the expected outcome; two of them provide confidence intervals with correct coverage.
topic linear regression model
log-normal distribution
heteroscedasticity
biomarkers of inflammation
insulin resistance
simulation study
url http://www.mdpi.com/1660-4601/11/4/3521
work_keys_str_mv AT saragustavsson regressionmodelsforlognormaldatacomparingdifferentmethodsforquantifyingtheassociationbetweenabdominaladiposityandbiomarkersofinflammationandinsulinresistance
AT bjornfagerberg regressionmodelsforlognormaldatacomparingdifferentmethodsforquantifyingtheassociationbetweenabdominaladiposityandbiomarkersofinflammationandinsulinresistance
AT gerdsallsten regressionmodelsforlognormaldatacomparingdifferentmethodsforquantifyingtheassociationbetweenabdominaladiposityandbiomarkersofinflammationandinsulinresistance
AT evamandersson regressionmodelsforlognormaldatacomparingdifferentmethodsforquantifyingtheassociationbetweenabdominaladiposityandbiomarkersofinflammationandinsulinresistance
_version_ 1725464946049810432

Similar Items