To the Editor: Dr Levene and colleagues estimated how population health measures (frequency of smoking, number of physicians, etc) were related to coronary heart disease (CHD) mortality in 152 geographic regions of England.1 They used linear regression with the coronary mortality rate (deaths divided by the regional population estimate) as the outcome. All their explanatory variables were divided by the same regional population estimate: number of smokers/population, number of physicians/population, etc.
Cummings P. Population and Primary Health Care Characteristics and Coronary Heart Disease Mortality. JAMA. 2011;305(8):778-779. doi:10.1001/jama.2011.154