Document Detail

A simulation study of confounding in generalized linear models for air pollution epidemiology.
Jump to Full Text
MedLine Citation:
PMID:  10064552     Owner:  NLM     Status:  MEDLINE    
Abstract/OtherAbstract:
Confounding between the model covariates and causal variables (which may or may not be included as model covariates) is a well-known problem in regression models used in air pollution epidemiology. This problem is usually acknowledged but hardly ever investigated, especially in the context of generalized linear models. Using synthetic data sets, the present study shows how model overfit, underfit, and misfit in the presence of correlated causal variables in a Poisson regression model affect the estimated coefficients of the covariates and their confidence levels. The study also shows how this effect changes with the ranges of the covariates and the sample size. There is qualitative agreement between these study results and the corresponding expressions in the large-sample limit for the ordinary linear models. Confounding of covariates in an overfitted model (with covariates encompassing more than just the causal variables) does not bias the estimated coefficients but reduces their significance. The effect of model underfit (with some causal variables excluded as covariates) or misfit (with covariates encompassing only noncausal variables), on the other hand, leads to not only erroneous estimated coefficients, but a misguided confidence, represented by large t-values, that the estimated coefficients are significant. The results of this study indicate that models which use only one or two air quality variables, such as particulate matter [less than and equal to] 10 microm and sulfur dioxide, are probably unreliable, and that models containing several correlated and toxic or potentially toxic air quality variables should also be investigated in order to minimize the situation of model underfit or misfit.
Authors:
C Chen; D P Chock; S L Winkler
Publication Detail:
Type:  Journal Article    
Journal Detail:
Title:  Environmental health perspectives     Volume:  107     ISSN:  0091-6765     ISO Abbreviation:  Environ. Health Perspect.     Publication Date:  1999 Mar 
Date Detail:
Created Date:  1999-07-01     Completed Date:  1999-07-01     Revised Date:  2009-11-18    
Medline Journal Info:
Nlm Unique ID:  0330411     Medline TA:  Environ Health Perspect     Country:  UNITED STATES    
Other Details:
Languages:  eng     Pagination:  217-22     Citation Subset:  IM    
Affiliation:
Ford Research Laboratory, Dearborn, MI 48121 USA.
Export Citation:
APA/MLA Format     Download EndNote     Download BibTex
MeSH Terms
Descriptor/Qualifier:
Air Pollution / statistics & numerical data*
Bias (Epidemiology)
Computer Simulation*
Confidence Intervals
Confounding Factors (Epidemiology)
Data Interpretation, Statistical
Environmental Exposure / statistics & numerical data*
Linear Models
Research Design / standards*
Sample Size
Comments/Corrections

From MEDLINE®/PubMed®, a database of the U.S. National Library of Medicine

Full Text
Journal Information
Journal ID (nlm-ta): Environ Health Perspect
ISSN: 0091-6765
Article Information
Download PDF

Print publication date: Month: 3 Year: 1999
Volume: 107 Issue: 3
First Page: 217 Last Page: 222
ID: 1566403
PubMed Id: 10064552

A simulation study of confounding in generalized linear models for air pollution epidemiology.
C Chen
D P Chock
S L Winkler
Ford Research Laboratory, Dearborn, MI 48121 USA.



Article Categories:
  • Research Article


Previous Document:  Exposure to indoor background radiation and urinary concentrations of 8-hydroxydeoxyguanosine, a mar...
Next Document:  Indoor, outdoor, and regional summer and winter concentrations of PM10, PM2.5, SO4(2)-, H+, NH4+, NO...