Parameter estimation and computation of the Fisher information matrix for functions of phase type random variables

Celeste R. Pavithra and T.G. Deepak

Computational Statistics & Data Analysis, 2022, vol. 167, issue C

Abstract: Parameter estimation and statistical inference for the phase type (PH) class of distributions are significantly important while considering the role of PH random variables in stochastic models appearing across various disciplines. Estimation of the parameters and computation of the Fisher Information Matrix (FIM) for some functions of PH random variables g(X), which are random variables of the continuous type is the main objective here. The following two cases are considered: (i) the set g−1(y) has at most a finite number of elements for every real y and (ii) for every real number y,g−1(y) has either a countably infinite number of elements that form an arithmetic progression or no element. The parameter estimation and the FIM computation for some random variables which can be obtained as functions of the PH random variables are carried out numerically for illustrative purposes. Also, some standard distributions like Pareto and beta as well as some real life data are shown to be approximated by appropriate functions of phase type random variables.

Keywords: EM algorithm; Estimation of parameters; Finite support phase type distributions; Fisher information; Functions of PH random variables (search for similar items in EconPapers)
Date: 2022
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://www.sciencedirect.com/science/article/pii/S0167947321001961
Full text for ScienceDirect subscribers only.

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:eee:csdana:v:167:y:2022:i:c:s0167947321001961

DOI: 10.1016/j.csda.2021.107362

Access Statistics for this article

Computational Statistics & Data Analysis is currently edited by S.P. Azen

More articles in Computational Statistics & Data Analysis from Elsevier
Bibliographic data for series maintained by Catherine Liu ().