Bypassing the selection rule in choosing controls for a case-control study
Bypassing the selection rule in choosing controls for a case-control study
Objectives It has been argued that in case–control studies, controls should be drawn from the base population that gives rise to the cases. In designing a study of occupational injury and risks arising from long-term illness and prescribed medication, we lacked data on subjects' occupation, without which employed cases (typically in manual occupations) would be compared with controls from the general population, including the unemployed and a higher proportion of white-collar professions. Collecting the missing data on occupation would be costly. We estimated the potential for bias if the selection rule were ignored.
Methods: We obtained published estimates of the frequencies of several exposures of interest (diabetes, mental health problems, asthma, coronary heart disease) in the general population, and of the relative risks of these diseases in unemployed versus employed individuals and in manual versus non-manual occupations. From these we computed the degree of over- or underestimation of exposure frequencies and exposure ORs if controls were selected from the general population.
Results: The potential bias in the OR was estimated as likely to fall between an underestimation of 14% and an overestimation of 36.7% (95th centiles). In fewer than 6% of simulations did the error exceed 30%, and in none did it reach 50%.
Conclusions: For the purposes of this study, in which we were interested only in substantial increases in risk, the potential for selection bias was judged acceptable. The rule that controls should come from the same base population as cases can justifiably be broken, at least in some circumstances.
872-877
Palmer, Keith T.
0cfe63f0-1d33-40ff-ae8c-6c33601df850
Kim, Miranda
c2e4ad50-0a64-4da9-8335-78531d88e93d
Coggon, David
2b43ce0a-cc61-4d86-b15d-794208ffa5d3
December 2010
Palmer, Keith T.
0cfe63f0-1d33-40ff-ae8c-6c33601df850
Kim, Miranda
c2e4ad50-0a64-4da9-8335-78531d88e93d
Coggon, David
2b43ce0a-cc61-4d86-b15d-794208ffa5d3
Palmer, Keith T., Kim, Miranda and Coggon, David
(2010)
Bypassing the selection rule in choosing controls for a case-control study.
Occupational & Environmental Medicine, 67 (12), .
(doi:10.1136/oem.2009.050674).
(PMID:20864466)
Abstract
Objectives It has been argued that in case–control studies, controls should be drawn from the base population that gives rise to the cases. In designing a study of occupational injury and risks arising from long-term illness and prescribed medication, we lacked data on subjects' occupation, without which employed cases (typically in manual occupations) would be compared with controls from the general population, including the unemployed and a higher proportion of white-collar professions. Collecting the missing data on occupation would be costly. We estimated the potential for bias if the selection rule were ignored.
Methods: We obtained published estimates of the frequencies of several exposures of interest (diabetes, mental health problems, asthma, coronary heart disease) in the general population, and of the relative risks of these diseases in unemployed versus employed individuals and in manual versus non-manual occupations. From these we computed the degree of over- or underestimation of exposure frequencies and exposure ORs if controls were selected from the general population.
Results: The potential bias in the OR was estimated as likely to fall between an underestimation of 14% and an overestimation of 36.7% (95th centiles). In fewer than 6% of simulations did the error exceed 30%, and in none did it reach 50%.
Conclusions: For the purposes of this study, in which we were interested only in substantial increases in risk, the potential for selection bias was judged acceptable. The rule that controls should come from the same base population as cases can justifiably be broken, at least in some circumstances.
Text
OEM_2010_Bypassing_selection_rule_in_cc_studies.pdf
- Version of Record
More information
Published date: December 2010
Identifiers
Local EPrints ID: 187999
URI: http://eprints.soton.ac.uk/id/eprint/187999
ISSN: 1351-0711
PURE UUID: 12d28025-ffa9-4dd7-9f4f-114ac7ca467d
Catalogue record
Date deposited: 19 May 2011 13:18
Last modified: 15 Mar 2024 02:52
Export record
Altmetrics
Contributors
Author:
Keith T. Palmer
Author:
Miranda Kim
Author:
David Coggon
Download statistics
Downloads from ePrints over the past year. Other digital versions may also be available to download e.g. from the publisher's website.
View more statistics