Author(s):
1. M.A.T. ElShahat:
Faculty of Business University Jeddah, Kingdom of Saudi Arabia.
2. A.A.M. Mahmoud:
Faculty of Commerce, Azhar University, Egypt
Abstract:
The use of finite mixture distributions, to control for unobserved heterogeneity, has become increasingly popular among those estimating dynamic discrete choice models. One of the barriers to using mixture models is that parameters that could previously be estimated in stages must now be estimated jointly: using mixture distributions destroys any additive reparability of the log likelihood function. In this research, Bayesian estimators have been obtained for the parameters of the mixture of exponentiated Weibull distribution when sample is available from censoring scheme. The maximum likelihood estimators of the parameters and the asymptotic variance covariance matrix have been obtained by Elshahat and Mahmoud (2016). Bayes and approximate Bayes (Lindley's form) estimators have been developed under squared error loss function as well as under LINEX loss function using non -informative type of priors for the parameters will be obtained. A numerical illustration for these new results is given.
Page(s):
709-737
DOI:
DOI not available
Published:
Journal: Pakistan Journal of Statistics and Operation Research, Volume: 12, Issue: 4, Year: 2016
Keywords:
maximum likelihood estimation
,
Bayesian estimation
,
and phrases
,
Mixture of two exponentiated Weibull distribution MTEW
,
Approximate Bayesian estimation
,
Lindley approximation MonteCarlo simulation
References:
References are not available for this document.
Citations
Citations are not available for this document.