Comparison of methods of point estimation in occupational epidemiologic studies

Authors
Citation
Jt. Lee et Bck. Choi, Comparison of methods of point estimation in occupational epidemiologic studies, YONSEI MED, 40(1), 1999, pp. 46-55
Citations number
45
Categorie Soggetti
General & Internal Medicine
Journal title
YONSEI MEDICAL JOURNAL
ISSN journal
05135796 → ACNP
Volume
40
Issue
1
Year of publication
1999
Pages
46 - 55
Database
ISI
SICI code
0513-5796(199902)40:1<46:COMOPE>2.0.ZU;2-C
Abstract
Two common study designs of occupational epidemiologic studies are cohort m ortality studies, which use the population at risk as a denominator, and pr oportionate mortality studies, which use the total number of events as a de nominator. This study compared the various methods of point estimation for cohort mortality studies, i.e., RR (risk ratio), OR (odds ratio) and SMR (s tandardized mortality ratio), and those for proportionate mortality studies , i.e., PRR (proportionate risk ratio), FOR (proportionate odds ratio) and PMR (proportionate mortality ratio). This study was based on a real dataset of all workers in Metropolitan Toronto, Canada, who applied for compensati on for various types of injuries or diseases from the Workers' Compensation Board in 1980. Results showed that within the cohort mortality or proporti onate mortality study designs, OR (or FOR) in all cases gave the least cons ervative estimates (farthest away from the null value), while SMR (or PMR) gave the most conservative estimates. The empirical differences between the point estimators were generally small. Our results showed that between stu dy designs the corresponding point estimators were poorly correlated. In ad dition, this empirical study indicated that the use of the mortality odds r atio did not improve the proportionate mortality study very much in terms o f generating results similar to the risk ratio from the cohort mortality de sign. We drew two conclusions: first, the point estimators within each stud y design can generally be a good alternative to one another; and second, pr oportionate mortality studies are not a good approximation for cohort morta lity studies.