Applying the Polynomial Maximization Method to Estimate ARIMA Models with Asymmetric Non-Gaussian Innovations

TL;DR

The paper introduces PMM2, a semiparametric method for estimating ARIMA models with asymmetric, non-Gaussian innovations, outperforming classical methods especially with moderate asymmetry.

Contribution

Develops and validates PMM2, a novel polynomial maximization approach that exploits higher-order moments for ARIMA estimation with non-Gaussian innovations.

Findings

PMM2 outperforms classical methods for asymmetric innovations.

Achieves 37-47% variance reduction in efficiency for certain distributions.

Matches OLS efficiency under Gaussian innovations, with comparable computational costs.

Abstract

Classical estimators for ARIMA parameters (MLE, CSS, OLS) assume Gaussian innovations, an assumption frequently violated in financial and economic data exhibiting asymmetric distributions with heavy tails. We develop and validate the second-order polynomial maximization method (PMM2) for estimating ARIMA$(p,d,q)$ models with non-Gaussian innovations. PMM2 is a semiparametric technique that exploits higher-order moments and cumulants without requiring full distributional specification. Monte Carlo experiments (128,000 simulations) across sample sizes $N \in \{100, 200, 500, 1000\}$ and four innovation distributions demonstrate that PMM2 substantially outperforms classical methods for asymmetric innovations. For ARIMA(1,1,0) with $N=500$, relative efficiency reaches 1.58--1.90 for Gamma, lognormal, and $\chi^2(3)$ innovations (37--47\% variance reduction). Under Gaussian innovations PMM2 matches OLS efficiency, avoiding the precision loss typical of robust estimators. The method delivers major gains for moderate asymmetry ($|\gamma_3| \geq 0.5$) and $N \geq 200$, with computational costs comparable to MLE. PMM2 provides an effective alternative for time series with asymmetric innovations typical of financial markets, macroeconomic indicators, and industrial measurements. Future extensions include seasonal SARIMA models, GARCH integration, and automatic order selection.