TITLE:
Consistency of the φ-Divergence Based Change Point Estimator
AUTHORS:
Mwelu Susan, Anthony G. Waititu, Peter N. Mwita, Charity Wamwea
KEYWORDS:
Change Point, Consistency, φ-Divergence, Kullback-Leibler, Generalized Pareto Distribution
JOURNAL NAME:
Open Journal of Statistics,
Vol.10 No.5,
October
27,
2020
ABSTRACT: This paper utilizes a change-point estimator based
on the φ-divergence. Since we seek a near perfect translation
to reality, then locations of parameter change within a finite set of data have
to be accounted for since the assumption of stationary model is too restrictive especially for long time series. The estimator is
shown to be consistent through asymptotic theory and finally proven through
simulations. The estimator is applied to the generalized Pareto distribution to
estimate changes in the scale and shape parameters.