Cost effectiveness calculations and sample size

This is one of an occasional series of notes on economics

Clinical trials should be large enough to detect a clinically important difference between two treatments. Yet a clinically important difference is often difficult to define and debatable. This difficulty may explain why so few published trials report the clinical reasoning underlying their sample size selection. Furthermore, clinical investigators are often suspected of approaching sample size calculations logistically rather than clinically: they estimate the number of patients who can be recruited into a trial and then ask a statistician to justify the sample size by calculating the “detectable” difference implied by the number of recruitable patients.1 Including economic criteria to aid sample size determination for clinical trials might improve the rigour of sample size selection. 2 3

Consider a recent randomised trial comparing the effectiveness of hysterectomy with hysteroscopic surgery for treating menorrhagia. 4 5 The trial found that hysteroscopic surgery …