Patterns of skewness risk

• Autor(a) principal: Alberto, Daniela Sofia dos Santos
• Data de Publicação: 2021
• Tipo de documento: Dissertação
• Idioma: eng
• Título da fonte: Repositório Científico de Acesso Aberto de Portugal (Repositórios Cientìficos)
• Texto Completo: http://hdl.handle.net/10071/24195
• topic: Skewness; Value at Risk; Market risk; Skewed Generalized t distribution; Generalised Pareto

The Skewed Generalised t (SGT), which has a bell shape, is more suitable to reflect market returns behaviour and its extreme drops and rises than the Normal distribution. This distribution is efficient in following the empirical distributions of financial returns, as it may incorporate high values of skewness and kurtosis, typically ignored by the normal distribution. This dissertation contributes to the investigation on skewness present in financial returns, by using stock indices as the object of analysis. The study focuses on identifying patterns of skewness in distributions with different time windows, time periods and frequencies. For the analysis, we use the SGT distribution, a five-parameter distribution initially introduced by Theodossiou (1998), to reflect the empirical distribution of returns into a parameterized distribution. To this end, the leading indices of the most traded currencies in the world were considered: FTSE 100, DAX 30, S&P 500 and Nikkei 225. The achieved results validate the hypothesis that the financial returns show a negative asymmetry, confirming that the SGT fits the empirical distribution better than the Normal distribution does. These outcomes are uplifting to use the SGT in parametric terms to estimate the Value at Risk (VaR) and future financial methodologies.