Partial autocorrelation parameterization for subset autoregression

TL;DR

This paper introduces a new partial autocorrelation plot and subset autoregressive models, providing a comprehensive framework for model identification, estimation, and diagnostics, especially useful for high-order autoregressions in long time series.

Contribution

It presents a novel partial autocorrelation plot and subset autoregressive models, enhancing model building for complex high-order autoregressions.

Findings

New partial autocorrelation plot improves model identification

Subset autoregressive models are more efficient for high-order series

Comprehensive methods for estimation and diagnostics are developed

Abstract

A new version of the partial autocorrelation plot and a new family of subset autoregressive models are introduced. A comprehensive approach to model identification, estimation and diagnostic checking is developed for these models. These models are better suited to efficient model building of high-order autoregressions with long time series. Several illustrative examples are given.