Abstract

Human mortality has various known and unknown reasons, some of which are predictable and affect small groups of people, while others come suddenly and affect a large group of people in a short time. Extreme events such as storms, earthquakes, pandemics, and Sonoma's are examples of such events. Many models have been presented for human mortality, each with some assumptions and requirements that might not hold in practice. Nonparametric models such as Singular Spectrum Analysis (SSA) can be used to overcome these limitations. This paper aims to investigate the use of SSA to capture the effect of extreme events on mortality models. Real datasets from European countries are used to demonstrate the effectiveness of the proposed method.