Graham, D.J. et al. 2005. Risk of acute myocardial infarction and sudden cardiac death in patients treated with cyclo-oxygenase 2 selective and non-selective non-steroidal anti-inflammatory drugs: nested case-control study. The Lancet 365: 475-481. Read Graham et al. (2005) with an eye toward finding examples of correlation, causation, confounding, control group, treatment group and controlled for.
Pease and Bull. 2000. Science for Business, Law and Journalism. Chapter 14. Correlations are hard to interpret. Chapter 16. Controls. Chapter 18 Experiments make the best controls.
You may also find it helpful to review the two chapters on models assigned for the previous class.
2. Drawing on the facts in Graham et al. (2005), use each of the following terms in a sentence: (i) correlation, (ii) causation, (iii) control group, (iv) treatment group, (v) controlled for, (vi) confounded (or confounding).
3. Graham et al. believe that confounding variables were not a significant problem in their study, a conclusion supported by a telephone survey they undertook. Explain why the data obtained from the telephone survey supports the view that Graham et al.'s results were not affected in a major way by confounding.