Are Randomized Double-Blind Experiments Everything?
Frank Hampel
Mathematics, Swiss Federal Institute of Technology (ETH), Zurich, Switzerland

The question of the effectiveness of various medical treatments is of general public interest. Unfortunately, the opinions are strongly divided, not only on the effectiveness of specific classes of treatments, but even on the criteria to be used.

One standard method of evaluation is the randomized double-blind experiment. It is designed to eliminate subjective biases which, as experience shows, are a big danger otherwise. One of the earliest and biggest such experiments was the 1954 Poliomyelitis Vaccine experiment described nicely in Tanur et al. (1972; later edition 1989). This article describes also some difficulties and weak points of this approach. Yet, the approach became a standard for many medical researchers, cf., e.g., Singh and Ernst (2008).

Nevertheless, the questions arise whether this approach is always possible; whether it is safe enough in practice; whether it is lastly philosophically unsound (cf. Hampel 2002); whether it is perhaps wasteful, leading to big avoidable damage; and whether it could perhaps be complemented or replaced by other, new methods, closer to common sense. This may require opening up to new experiences and giving up old “background beliefs” (Hampel 2009) in view of many new empirical observations. The elucidation of the prejudices hidden in old background beliefs may lead to a new outlook, also on many aspects of statistics.


Hampel, F. (2002): Some thoughts about classification. Invited keynote lecture, 8th Conference of the International Federation of Classification Societies, July 16-19, 2002, Cracow, Poland. In: K. Jajuga, A. Sokolowski and H.-H. Bock, eds.: Classification, Clustering, and Data Analysis. Recent Advances and Applications, pp. 5-26. Springer, Berlin. URL:

Hampel, F. (2009): How can we get new knowledge? In: T. Augustin, F. P. A. Coolen, S. Moral, and M. C. M. Troffaes, eds.: Proceedings of the Sixth International Symposium on Imprecise Probability: Theories and Applications. Durham University, Department of Mathematical Sciences, Durham, U.K. URL:

Singh, S., and Ernst, E. (2008): Trick or Treatment? Alternative medicine on trial. Bantam Books. Tanur, J.M., Mosteller, F., Kruskal, W.H., Link, R.F., Pieters, R.S., and Rising, G.R., eds. (1972): Statistics: A Guide to the Unknown. Holden-Day, San Francisco.

Keywords: medical treatments; randomized double-blind experiment; scientific inference; background belief

Biography: Dr. Dr. h.c. Frank Hampel is professor emeritus at the Swiss Federal Institute of Technology, Zurich, and member of the ISI. His main interests are and were robust statistics, including robustness against the violation of the independence assumption, data analysis and consulting, especially for biologists, and the philosophical foundations of statistics.