BAYESIAN STATISTICS AND EXPERIMENTS ON STOCHASTIC VARIABLES

If an observable x does no or only barely overcome the error inherent in an experiment designed to measure x then the extraction of informat ion, e.g., of an upper limit on x, is plagued with conceptual difficul ties. They are discussed in the present note. It is concluded that the bayesian concept offers a satisfactory answer. It is applied to the r eanalysis of tests on time-reversal symmetry breaking via detailed bal ance.