Jj. Deely et Jb. Keats, BAYES STOPPING RULES FOR RELIABILITY TESTING WITH THE EXPONENTIAL-DISTRIBUTION, IEEE transactions on reliability, 43(2), 1994, pp. 288-293
These rules for terminating testing involve achieving specified levels
of credibility in both: 1) the probability of the posterior estimate
of the exponential scale-parameter, theta, after some, m, of the units
have been tested, and 2) the mean of the probability of theta over th
e remaining units, when viewed pessimistically. Sample decision tables
and a numerical example illustrate both the sequential & batch testin
g cases. Large savings in test times can be achieved whenever the firs
t m units present strong evidence in favor of either hypothesis (H0: t
heta = theta0 vs H-1: theta = theta1, theta1 < theta0).