Some problems with sample size

When I began my career in medical statistics, back in 1972, little was heard of power calculations. In major journals, sample size often appeared to be whatever came to hand. For example, in that month, September 1972, the Lancet contained 31 research reports which used individual subject data, excluding case reports and animal studies. The median sample size was 33 (quartiles 12 and 85). In the British Medical Journal in September 1972, there were 30 reports of the same type, with median sample size 37 (quartiles 12 and 158). None of these publications reported any explanation of the choice of sample size, other than it being what was available. Indeed, statistical considerations were almost entirely lacking from the methods sections of these papers. One of the few that mentioned them at all (Bottiger and Carlson 1972) merely noted that ‘Statistical analyses were performed using methods described by Snedecor (1956)’, this being a standard statistical textbook.