—Dr Braun is correct in indicating the RR for coronary heart disease for the lowest folate level studied was statistically significant (P=.04) for women, but not for men. However, the test for trend was statistically significant for both men and women. Although stratum-specific RRs were higher for women compared with men, the 95% CIs around the point estimates for men and women overlapped. Moreover, a comparison of the sex-specific rate ratios is not the most appropriate means to assess interaction. To formally test the interaction of sex, folate, and coronary heart disease, we compared the goodness-of-fit of a model that incorporated this interaction with one that did not. The deviances were 581.76 and 584.53 for the "interaction" and "no-interaction" models, respectively. This difference can be assumed to follow a X2 distribution with degrees of freedom equal to the difference in the number of independent parameters in the 2
Morrison HI, Schaubel D, Desmeules M, Wigle DT. Serum Folate and Risk of Fatal Coronary Heart Disease-Reply. JAMA. 1996;276(15):1222. doi:10.1001/jama.1996.03540150024024
Customize your JAMA Network experience by selecting one or more topics from the list below.
Create a personal account or sign in to: