Idea: How people respond to treatment may vary from one subgroup to another–When is this a matter of chance or of undetected additional variables? How do we delineate the boundaries between subgroups?
Lagakos provides a statistician’s cautions about the significance of results derived from subgroups of the whole population, especially if the subgroups were only defined after exploring the data.
The opposite caution is that treating everyone as if they were from the same population (for good statistical reasons) distracts our attention from the clues that might lead us to seeing that the population is not one uniform whole, but is a mixture of types. This can have significant health care implications — see case studies about different kinds of breast cancer (Regan) and aspirin resistance.
Additional angles on heterogeneity are evident in Eikelboom 2003, Gum 2003, Kahn 2007, and Nelson 2005.
(This post continues a series laying out a sequence of basic ideas in thinking like epidemiologists, especially epidemiologists who pay attention to possible social influences on the development and unequal distribution of diseases and behaviors in populations [see first post in series and contribute to open-source curriculum http://bit.ly/EpiContribute].)
Eikelboom, J. W. and G. J. Hankey (2003). “Aspirin resistance: a new independent predictor of vascular events?” Journal of the American College of Cardiology 41: 966-968.
Gum, P. A., K. Kottke-Marchant, et al. (2003). “A prospective, blinded determination of the natural history of aspirin resistance among stable patients with cardiovascular disease.” Journal of the American College of Cardiology 41: 961-965.
Kahn, J. (2007). “Race in a Bottle.” Scientific American(July 15).
Lagakos, S. W. (2006). “The challenge of subgroup analysis–Reporting without distorting.” New England Journal of Medicine 354: 1667-1669.
Nelson, M. R., D. Liew, et al. (2005). “Epidemiological modelling of routine use of low dose aspirin for the primary prevention of coronary heart disease and stroke in those aged >=70.” British Medical Journal 330: 1306-1311.
Regan, M. M. and R. D. Gelber (2005). “Predicting response to systematic treatments: Learning from the past to plan for the future.” The Breast 14: 582-593.