Centro de Documentacion de Fundación MAPFRE - A Minimum variance approach to multivariate linear regression with application to actuarial problems

MAP20260002996

A Minimum variance approach to multivariate linear regression with application to actuarial problems / Zinoviy Landsman and Udi Makov

Sumario: This article introduces a new multivariate linear regression approach based on minimizing the variance of the squared distance (MVS), as an alternative to the classical minimum expected squared deviation (MES) criterion. The methodology enhances the accuracy of predicting risk vectors when the underlying distributions are non-symmetric by incorporating third-order moment information. Closed-form analytical expressions for the estimators are derived, and the method is shown to significantly reduce prediction variability. The study includes two real-world applications-fire insurance losses and stock index returns-demonstrating the potential of this approach for actuarial and financial modeling

En: European Actuarial Journal. - Cham, Switzerland : Springer Nature Switzerland AG, 2021-2022. - 11/08/2025 Volume 15 - Number 2 - August 2025 , p. 899 - 920

1. Modelos actuariales . 2. Análisis multivariante . 3. Riesgo financiero . 4. Métodos estadísticos . 5. Análisis de varianza . 6. Dependencia . I. Makov, Udi E. . II. Springer . III. Título.