Modelagem da volatilidade condicional incorporando o período não regular do pregão ao modelo APARCH: um estudo com ações listadas na BM&FBOVESPA

Detalhes bibliográficos
Ano de defesa: 2017
Autor(a) principal: Breno Valente Fontes Araujo
Orientador(a): Não Informado pela instituição
Banca de defesa: Não Informado pela instituição
Tipo de documento: Dissertação
Tipo de acesso: Acesso aberto
Idioma: por
Instituição de defesa: Universidade Federal de Minas Gerais
UFMG
Programa de Pós-Graduação: Não Informado pela instituição
Departamento: Não Informado pela instituição
País: Não Informado pela instituição
Palavras-chave em Português:
Link de acesso: http://hdl.handle.net/1843/BUOS-APPQ9G
Resumo: The volatility has enough notability in the studies of Finance because it is a fundamental parameter in derivatives pricing, efficient allocation of portfolios, and risk management. Believing that during the non-regular trading hours occurs the arrival of important information capable of impacting on the volatility of the day, this study aims to evaluate how the after-market and pre-opening periods impact on estimation of conditional volatility a day ahead. For this, we used the APARCH model, of the ARCH family, incorporating the after-market, pre-opening and total Overnight periods, to assess if them carry important information for modeling the volatility. We analyzed the 20 stocks of Brazilian companies listed on the BM&FBovespa and belonging to the BR TITANS 20 with ADRs listed in the stock exchanges of New York and on NASDAQ, in the period from January 1, 2010 until 24 July 2015, from intraday data at 15 minute intervals. The results were evaluated in-sample by the AICc information criterium and the statistical significance of the coefficients, and out-of-sample by RMSE, MAPE and R ² of the regression of Mincer Zarnowitz. The analysis of the results both in and out-of-sample does not allow to claim the best model, because there is no unanimity among all the stocks, however, in both analyses, non-regular trading hours showed to incorporate important information for most stocks. Furthermore, the models that incorporated the pre-opening period obtained, in general, superior results to the models that incorporated the after-market period, demonstrating that this period carries important information for conditional volatility forecast.