Premium
Predicted mortality patterns in cohort study populations exposed to different types of hazard: Can SMRS show a dose‐response?
Author(s) -
Bell C. M. Janine,
Coleman Derek A.
Publication year - 1983
Publication title -
statistics in medicine
Language(s) - English
Resource type - Journals
SCImago Journal Rank - 1.996
H-Index - 183
eISSN - 1097-0258
pISSN - 0277-6715
DOI - 10.1002/sim.4780020308
Subject(s) - hazard ratio , statistics , estimator , cohort , hazard , confidence interval , demography , cohort study , medicine , hazard model , proportional hazards model , econometrics , mathematics , biology , ecology , sociology
The analysis of data from cohort studies by duration of exposure and time since first exposure (latent interval) has been investigated using a simulation approach. These two analyses are often performed when the estimator of risk, commonly the O/E ratio or SMR, shows evidence of a raised risk. Two measures of risk were tested in the detailed analyses: the O/E ratio and the excess death rate. The latter was found to reflect the ‘dose‐response’ relationship more accurately for a variety of hazard types. Attention is drawn to possible biases and to the importance of adjustment for age in these analyses.