Changepoint detection in autocorrelated ordinal categorical time series

Abstract

This article considers changepoint detection in serially correlated categorical time series. While changepoint aspects in correlated sequences of continuous random variables have been extensively explored in the literature, changepoint methods for independent categorical time series are only now coming into vogue. This study extends changepoint methods by developing techniques for correlated categorical time series. Here, a cumulative sum type test is devised to test for a single changepoint in a correlated categorical data sequence. Our categorical series is constructed from a latent Gaussian process through clipping techniques. A sequential parameter estimation method is proposed to estimate the parameters in this model. The methods are illustrated via simulations and applied to a real categorized rainfall time series from Albuquerque, New Mexico.

Generalized gamma ARMA process for synthetic aperture radar amplitude and intensity data

“…From an unconditional point of view, Mello et al (2022) have proposed the first-order Gamma-Lindley process for describing hydrology data. Li and Lu (2022) have worked with categorical time series to detect changes in precipitation. In terms of conditional models, Benjamin et al (2003) proposed a conditional autoregressive moving average (ARMA) process, called generalized ARMA (GARMA), whose marginal distribution is a member of the exponential family (FE).…”