Practical guides to understanding sample size and minimal clinically important difference (MCID).

s presented at the AAO-HNS Annual Meeting. Otolaryngol Head Neck Surg 2006;135:197–203. 3. Karri V. Randomised clinical trials in plastic surgery: survey of output and quality of reporting. J Plast Reconstr Aesthet Surg 2006;59:787–96. 4. Bhattacharyya N. Peer review: studying the major otolaryngology journals. Laryngoscope 1999;109:640–4. 5. Noordzij J, Affleck B. Coblation versus unipolar electrocautery tonsillectomy: a prospective, randomized, single-blind study in adult patients. Laryngoscope 2006;116:1303–9. 6. Norman G, Sloan J, Wyrwich K. Interpretation of changes in healthrelated quality of life: the remarkable universality of half a standard deviation. Med Care 2003;41:582–92.Figure 5 Illustration of how the data scale used for the outcomemeasure affects the required sample size. Note how much smallerthe sample size is when using a continuous variable to measure theoutcome than when using a dichotomous variable when keepingthe difference between means (continuous variable) and the dif-ference between proportions (dichotomous variable) the same.This generally holds true; however, there are exceptions, depen-dent upon the biology of the situation.18Otolaryngology–Head and Neck Surgery, Vol 136, No 1, January 2007