Confidence Intervals for Independent Exponential Series Systems
Gerald J. Lieberman, Sheldon M. Ross
Journal of the American Statistical Association · 1971 · Volume 66 · Issue 336
DOI: 10.1080/01621459.1971.10482354
Abstract
Suppose X 1 , X 2 , ···, X n are independent identically distributed exponential random variables with parameter λ 1 . Let Y 1 , Y 2 , ···, Y m also be independent identically distributed exponential random variables with parameter λ 2 , and assume that X's and Y's are independent. The problem is to estimate R(t) = e −(λ 1 +λ 2 )t . A procedure for determining on exact (1 − α) level lower confidence bound for R(t) is presented. let U = min(Σ n t = 1 X i , Σ m i = 1 Y i ), and K = {largest i ≤ n : Σ j i − 1 X i ≤ U} + {Largest i ≤ m : Σ j i = 1 Y i ≤ U}. Then given K = k, it is shown that U has a gamma distribution with parameters k and λ 1 + λ 2 . Hence, a lower confidence bound for R(t) can be obtained. The suggested procedure is then compared with others presented in the literature.
Enable JavaScript for citation tools and additional paper interactions.