It has been emphasized by several authors (see for example this reference) that testing for baseline differences between the treatment and control group is meaningless when patients have been correctly randomized to the groups. Still, the presentation of such p-values are still common also in high impact journals.

Knol et al. (1) reviewed all 1175 articles on randomized trials published during 2008-2010 in Annals of Internal Medicine, British Medical Journal (BMJ), Circulation, European Heart Journal, Journal of the American Medical Association (JAMA), Lancet, and the New England Journal of Medicine (NEJM).

Overall 388 (35%) of the reviewed articles presented baseline test results. However, this was substantially more common in the two American journals JAMA (59%) and NEJM (54%) than in the two British ones BMJ (8%) and the Lancet (2%).

The authors conclude that researchers and editors should change this erroneous practice.


Knol MJ, Groenwold RHH, Grobbee DE. P-values in baseline tables of randomised controlled trials are inappropriate but still common in high impact journals. Eur J Prev Cardiol 2012;19:231-232.