scientific article; zbMATH DE number 3965263
We discuss the negative binomial process which changes its intensity stepwise at a certain moment of time (the moment of disorder). The Cramer-Rao inequality is usually used to determine the accuracy of parameter estimation. The application of this inequality requires, however, the density function to fulfil particular conditions of regularity. The necessary conditions, which must be satisfied by the density of distribution, are not fulfilled in the problem in which the moment of a stepwise change of the statistical characteristic of a signal is the estimated parameter. Basing on the inequality proposed by Kiefer, we find the accurate lower variance bound of the disorder moment estimator. In our calculations we use the method presented in \textit{V. A. Pertel}', The greatest lower bound of the variance of an estimate of the instant of disruption of a Poisson flow. Izv. Akad. Nauk SSSR, Tekh. Kibern. 1971, No.5, 167-170 (1971).
- On the disorder problem for a negative binomial process
- Lower bounds on estimator performance for energy-invariant parameters of multidimensional Poisson processes
- Disorder problem for a Poisson process in the generalized Bayesian setting
- Some results on lower variance bounds useful in reliability modeling and estimation
- Efficient Sequential Estimation in a Nonhomogeneous Poisson Process
This page was built for publication:
Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3732799)