Minerva enjoys a good foot massage, but results from a small, single blind trial of reflexology for irritable bowel syndrome do little to dispel her scepticism about the therapy. Reflexology made no difference—statistically or clinically—to the experience of pain, altered bowel habit, or abdominal distension (British Journal of General Practice 2002;52:19-23). As this trial was designed in consultation with reflexology practitioners, their claims of success in cases where orthodox medicine has failed may have to be reassessed.

How confounding factors are dealt with statistically is of interest to readers who really want to know how a study was analysed. A cross sectional study of more then 500 original articles (published in 34 scientific medical journals) found that up to 45% of them offered the reader inadequate information about the statistical methods used. Articles that did better tended to include an author affiliated with a department of statistics, epidemiology, or public health. Such articles were published in journals with a higher impact factor (Annals of Internal Medicine 2002;136:122-6).

It's fascinating that someone who has passed on herpes to a lover can be charged with grievous bodily harm. Minerva can't be the only one who is curious about what went on behind the scenes for one such case to …