EM Estimation of a Non-identifiable Stochastic Frontier Model
The paper considers recently used truncated bivariate normal distribution that relaxes the basic assumption of independence between error components in stochastic frontier model. As shown by Bandyopadhyay and Das (2006) the model is not identifiable under a specific parametric configuration of the distribution. However, certain restriction on parameters can make it identifiable. Rather than imposing identifiability constraints on the parameters, the popularly used expectation – maximization (EM) algorithm is adopted as a general solution to estimate those parameters of the model. The performance and efficiency of the resulting estimator under EM algorithm with the restricted maximum likelihood estimator is assessed through a Monte Carlo simulation study. Finally, an illustration is provided by applying the model with this estimation procedure to the US electricity utility data.
Disclaimer/Regarding indexing issue:
We have provided the online access of all issues and papers to the indexing agencies (as given on journal web site). It’s depend on indexing agencies when, how and what manner they can index or not. Hence, we like to inform that on the basis of earlier indexing, we can’t predict the today or future indexing policy of third party (i.e. indexing agencies) as they have right to discontinue any journal at any time without prior information to the journal. So, please neither sends any question nor expects any answer from us on the behalf of third party i.e. indexing agencies.Hence, we will not issue any certificate or letter for indexing issue. Our role is just to provide the online access to them. So we do properly this and one can visit indexing agencies website to get the authentic information.