Measurement error in a multi-level analysis of air pollution and health: a simulation study.
Air pollution
Long-term
Measurement error
Multi-level models
Short-term
Simulations
Journal
Environmental health : a global access science source
ISSN: 1476-069X
Titre abrégé: Environ Health
Pays: England
ID NLM: 101147645
Informations de publication
Date de publication:
14 02 2019
14 02 2019
Historique:
received:
30
07
2018
accepted:
28
11
2018
entrez:
16
2
2019
pubmed:
16
2
2019
medline:
8
3
2019
Statut:
epublish
Résumé
Spatio-temporal models are increasingly being used to predict exposure to ambient outdoor air pollution at high spatial resolution for inclusion in epidemiological analyses of air pollution and health. Measurement error in these predictions can nevertheless have impacts on health effect estimation. Using statistical simulation we aim to investigate the effects of such error within a multi-level model analysis of long and short-term pollutant exposure and health. Our study was based on a theoretical sample of 1000 geographical sites within Greater London. Simulations of "true" site-specific daily mean and 5-year mean NO In general, health effect estimates associated with both long and short-term exposure were biased towards the null with the level of bias increasing to over 60% as the correlation coefficient decreased from 0.9 to 0.5 and the variance ratio increased from 0.5 to 2. However, for a combination of high correlation (0.9) and small variance ratio (0.5) non-trivial bias (> 25%) away from the null was observed. Standard errors of health effect estimates, though unaffected by changes in the correlation coefficient, appeared to be attenuated for variance ratios > 1 but inflated for variance ratios < 1. While our findings suggest that in most cases modelling errors result in attenuation of the effect estimate towards the null, in some situations a non-trivial bias away from the null may occur. The magnitude and direction of bias appears to depend on the relationship between modelled and "true" data in terms of their correlation and the ratio of their variances. These factors should be taken into account when assessing the validity of modelled air pollution predictions for use in complex epidemiological models.
Sections du résumé
BACKGROUND
Spatio-temporal models are increasingly being used to predict exposure to ambient outdoor air pollution at high spatial resolution for inclusion in epidemiological analyses of air pollution and health. Measurement error in these predictions can nevertheless have impacts on health effect estimation. Using statistical simulation we aim to investigate the effects of such error within a multi-level model analysis of long and short-term pollutant exposure and health.
METHODS
Our study was based on a theoretical sample of 1000 geographical sites within Greater London. Simulations of "true" site-specific daily mean and 5-year mean NO
RESULTS
In general, health effect estimates associated with both long and short-term exposure were biased towards the null with the level of bias increasing to over 60% as the correlation coefficient decreased from 0.9 to 0.5 and the variance ratio increased from 0.5 to 2. However, for a combination of high correlation (0.9) and small variance ratio (0.5) non-trivial bias (> 25%) away from the null was observed. Standard errors of health effect estimates, though unaffected by changes in the correlation coefficient, appeared to be attenuated for variance ratios > 1 but inflated for variance ratios < 1.
CONCLUSION
While our findings suggest that in most cases modelling errors result in attenuation of the effect estimate towards the null, in some situations a non-trivial bias away from the null may occur. The magnitude and direction of bias appears to depend on the relationship between modelled and "true" data in terms of their correlation and the ratio of their variances. These factors should be taken into account when assessing the validity of modelled air pollution predictions for use in complex epidemiological models.
Identifiants
pubmed: 30764837
doi: 10.1186/s12940-018-0432-8
pii: 10.1186/s12940-018-0432-8
pmc: PMC6376751
doi:
Substances chimiques
Air Pollutants
0
Particulate Matter
0
Nitrogen Dioxide
S7G510RUBH
Types de publication
Journal Article
Research Support, Non-U.S. Gov't
Langues
eng
Sous-ensembles de citation
IM
Pagination
13Subventions
Organisme : Medical Research Council
ID : MR/N014464/1
Pays : United Kingdom
Références
Stat Med. 2006 Dec 30;25(24):4279-92
pubmed: 16947139
Biostatistics. 2009 Apr;10(2):258-74
pubmed: 18927119
Epidemiology. 2009 May;20(3):442-50
pubmed: 19289962
Biostatistics. 2011 Oct;12(4):610-23
pubmed: 21252080
Environ Health. 2011 Jun 22;10:61
pubmed: 21696612
Epidemiology. 2011 Sep;22(5):680-5
pubmed: 21716114
PLoS One. 2012;7(4):e34664
pubmed: 22529923
Air Qual Atmos Health. 2012 Jun;5(2):203-216
pubmed: 22662023
J Expo Sci Environ Epidemiol. 2015 Mar-Apr;25(2):160-6
pubmed: 23571405
Am J Respir Crit Care Med. 2013 Jun 1;187(11):1226-33
pubmed: 23590261
BMC Med Res Methodol. 2013 Nov 13;13:136
pubmed: 24219031
Environmetrics. 2013 Dec 1;24(8):501-517
pubmed: 24764691
J Expo Sci Environ Epidemiol. 2015 Mar-Apr;25(2):138-44
pubmed: 24896768
BMJ Open. 2015 May 11;5(5):e006946
pubmed: 25967992
Biostatistics. 2016 Apr;17(2):377-89
pubmed: 26621845
Environ Health. 2016 Nov 25;15(1):114
pubmed: 27884187
Stat Med. 1998 Oct 15;17(19):2157-77
pubmed: 9802176
Occup Environ Med. 1998 Oct;55(10):651-6
pubmed: 9930084