Numerical Determination of the Distributions of Stopping Variables Associated with Sequential Procedures for Detecting Epochs of Shift in Distributions of Discrete Random Variables.
Abstract
Algorithms for the determination of the distribution functions of stopping variables are developed, for three types of sequential detection procedure. The first type is a Bayes quickest detection procedure. The second type is based on the crossing of linear boundaries by sample sums. The third type is a one-sided CUSUM control procedure. Approximations which particularly designed for computer application are given for the first type of stopping variables. Wiener process approximations, which significantly reduce the amount of computations required for the other two types of variables, are given. (Author)
Document Details
- Document Type
- Technical Report
- Publication Date
- Feb 01, 1973
- Accession Number
- AD0755758
Entities
People
- Shelemyahu Zacks
Organizations
- Case Western Reserve University