Copyright © 2026 Authors retain the copyright of this article. This article is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited.

@article{209866,
        author = {Nagendra Marisetty and Dr. Rajeshwari G M and Dr. P V Raveendra and Dr. S V Ramana Rao},
        title = {Robust Regression Analysis of International Metal Futures Outliers, Return Relationships and Gold Market Linkages},
        journal = {International Journal of Innovative Research in Technology},
        year = {2026},
        volume = {13},
        number = {5},
        pages = {3474-3495},
        issn = {2349-6002},
        url = {https://ijirt.org/article?manuscript=209866},
        abstract = {The study investigates the behavior of price, return, dependence, stationarity, outliers and robust regression of nine international metal futures (Aluminium, Copper, Gold, Lead, Palladium, Platinum, Silver, Tin and Zinc) in the period 2021-2025. The analysis employs descriptive statistics, Pearson’s correlation coefficients, Augmented Dickey-Fuller (ADF), DF-GLS, Phillips-Perron (PP) and Kwiatkowski-Phillips-Schmidt-Shin (KPSS) tests and various outlier detection methods. The results show that the metals have significantly different return behavior and volatility. Correlation analysis shows that most metal futures move in the same direction. The stationarity tests indicate that monthly returns should be employed in econometric modeling. However, the results of the outlier detection differ in the Tukey, the Mean / Standard Deviation, Autoregressive Moving Average (ARMA) and the Wavelet methods, which shows the importance of the use of proper diagnostic techniques to detect extreme market observations.
In this study, we also use M-estimation, S-estimation, and MM-estimation, which are robust regression methods, and Huber Type-I, Type-II, and Type-III standard errors and covariance specifications to check the relationships between the returns of Gold and the returns of the other metals. For the main robust regression specifications, the results are positive associations for gold returns with Copper and Silver returns and a negative association for gold returns with Lead returns. Given the strength of the statistical significance to alternative covariance specifications, we recommend MM-estimation with Huber Type-I covariance estimates as the preferred specification with Andrews M-estimation providing a useful robustness check. Finally, the results add to the knowledge of risk features and linkages of international metal futures markets, and have implications for portfolio diversification and commodity risk management.},
        keywords = {International Metal Futures, Gold, Robust Regression, M-Estimation, S-Estimation, MM-Estimation.},
        month = {October},
        }