ABSTRACT
A new decision function is proposed and its Bayes sampling plan is also derived in which cost of unit time is considered in the loss. The proposed sampling plan includes the Lam's (Lam, Y. Bayesian Variable Sampling Plans for the Exponential Distribution with Type I Censoring. Ann. Statist. 1994, 22(2), 696–711.) plan as a special case. An algorithm for determining an optimal sampling plan
is given and some optimal solutions are tabulated. Some numerical comparisons between the optimal sampling rule in Lam (Lam, Y. Bayesian Variable Sampling Plans for the Exponential Distribution with Type I Censoring. Ann. Statist. 1994, 22(2), 696–711.), the proposed rule and another alternative rule are also made. Some simple illustration for application is given.
ACKNOWLEDGMENT
The authors are grateful to a referee for his helpful comments.