Estimating function method for product autoregressive models. Issue 5 (28th May 2017)

• Record Type: Journal Article
• Authors: Balakrishna, N.; Muhammed, P. Anvar
• Is Part Of: Communications in statistics. Volume 46:Issue 5(2017)
• Page Start: 3962
• Page End: 3979
• Publication Date: 2017-05-28
• Subjects: Asymptotic optimality -- Estimating functions -- Nonlinear time series -- Product auto regression; Primary 62M10 -- Secondary 62F10; Mathematical statistics -- Periodicals; Mathematical statistics -- Data processing -- Periodicals; Digital computer simulation -- Periodicals; 519.5
• DOI: 10.1080/03610918.2015.1076468
• Languages: English
• ISSNs: 0361-0918

Abstract

ABSTRACT: The first-order product autoregressive (PAR(1)) model introduced by McKenzie in1982 did not attract the attention of practitioners due to the unavailability of a proper estimation method. This article proposes an estimating function (EF) method to fill the gap. In particular, we suggest an optimal combination of linear and quadratic EFs to overcome the problem of parameter identification. The procedure is applied to Weibull and Gamma PAR(1) models. Simulation and data analysis show that the proposed method performs better than the existing methods.