| Name: | Description: | Size: | Format: | |
|---|---|---|---|---|
| 821.19 KB | Adobe PDF |
Authors
Advisor(s)
Abstract(s)
Pretendeu-se com este estudo analisar o efeito dos dias da semana nas rendibilidades diárias do índice S&P 500 para o período de 11 de janeiro de 2016 a 15 de dezembro de 2023. Para tal, aplicou-se um modelo de heterocedasticidade condicionada GARCH – Generalized Autoregressive Conditional Heteroskedaticity Model, com variáveis dummy para todos os dias da semana menos a sexta-feira para evitar problemas de
multicolinearidade. A importância deste estudo enquadra-se na possibilidade de verificação da Hipótese de Mercado Eficiente desenvolvida por Fama, segundo a qual o mercado absorve quaisquer padrões ou efeitos repetitivos que venham a ser conhecidos, incapacitando a possibilidade de previsão de preços. Os resultados obtidos demonstraram que, à exceção de quarta-feira todos os dias da semana têm efeito na volatilidade das
rendibilidades. Verificou-se adicionalmente a presença de clusters da volatilidade no índice, o que fundamenta a utilidade do modelo estatístico aplicado.
The aim of this study was to analyze the weekdays effect on the daily returns of the S&P 500 index for the period from January 11, 2016, to December 15, 2023. To achieve the proposed goal, it was applied a Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model with dummy variables for all weekdays except for Friday to avoid multicollinearity issues. The context and importance of this study lie in the possibility of verifying the Efficient Market Hypothesis developed by Fama, which suggests that the market absorbs any known repetitive patterns or effects, thereby incapacitating the possibility of price prediction. The results obtained demonstrated that, except for Wednesday, all weekdays show to have effect on the volatility of returns. Additionally, the presence of volatility clusters in the index was observed, supporting the utility of the applied statistical model.
The aim of this study was to analyze the weekdays effect on the daily returns of the S&P 500 index for the period from January 11, 2016, to December 15, 2023. To achieve the proposed goal, it was applied a Generalized Autoregressive Conditional Heteroskedasticity (GARCH) model with dummy variables for all weekdays except for Friday to avoid multicollinearity issues. The context and importance of this study lie in the possibility of verifying the Efficient Market Hypothesis developed by Fama, which suggests that the market absorbs any known repetitive patterns or effects, thereby incapacitating the possibility of price prediction. The results obtained demonstrated that, except for Wednesday, all weekdays show to have effect on the volatility of returns. Additionally, the presence of volatility clusters in the index was observed, supporting the utility of the applied statistical model.
Description
Mestrado em Análise Financeira
Keywords
Efeito dos dias da semana Modelo GARCH Hipótese de mercado eficiente S&P 500 Clusters Weekdays effect GARCH model Efficient market hypothesis
Citation
Brito, F. V. (2024) O efeito dos dias da semana no índice S&P 500. [Dissertação de mestrado, Instituto Superior de Contabilidade e Administração de Lisboa]. Repositório Científico do Instituto Politécnico de Lisboa. http://hdl.handle.net/10400.21/17563