New Robust Estimation in Compound Exponential Weibull-Poisson Distribution for both contaminated and non-contaminated Data
Compound distributions
Exponential Weibull Poisson distribution
Maximum Likelihood method
EM algorithm
Downhill Simplex algorithm
Data contamination.
Abstract
The research Compared two methods for estimating fourparametersof the compound exponential Weibull - Poisson distribution which are the maximum likelihood method and the Downhill Simplex algorithm. Depending on two data cases, the first one assumed the original data (Non-polluting), while the second one assumeddata contamination. Simulation experimentswere conducted for different sample sizes and initial values of parameters and under different levels of contamination. Downhill Simplex algorithm was found to be the best method for in the estimation of the parameters, the probability function and the reliability function of the compound distribution in cases of natural and contaminateddata.
-norm Least Mean Square ( 