Volatility Forecasting before the Subprime Crisis

Felipe de Oliveira and Sinézio Fernandes Maia

No 10376, EcoMod2017 from EcoMod

Abstract: This paper aims to test the best model volatility forecasting using daily returns sample from Brazilian and US stock markets. This information is useful to portfolio managers and Central Bankers seeking to understand possible effects of policy interventions in financial markets. The period covered is from January of 2002 to December of 2007. The motivation to test the forecasting potency of these models comes from Engle and Patton (2001), where a good volatility model must be able to predict. The path followed was the same of Cavaleri (2008), which tested the most adherent with different characteristics and combinations (unconditional and conditional variances, and combinations). The sample period is from January of 2002 to December 2007. The database used are daily frequency prices of the Brazilian stock market’s index Bovespa and the Americans’ index is S&P 500. The models used are: i) unconditional volatility models: rolling window historical volatility and EWMA model; ii) conditional volatility models: Garch Family models (ARCH, GARCH, EGARCH, TGARCH); and, iii) forecasting combinations using OLS method. The preliminary results show evidences that EGARCH (2,1) to Brazil and EGARCH (5,4) to in the sample volatility forecasting. The next step is to use the combination of volatilities as well as use out-of-sample prediction.

Keywords: Brazil; Agent-based modeling; Agent-based modeling (search for similar items in EconPapers)
Date: 2017-07-04
References: View references in EconPapers View complete reference list from CitEc
Citations:

Downloads: (external link)
http://ecomod.net/system/files/RiskForecastingEcomodelling2017.pdf

Related works:
This item may be available elsewhere in EconPapers: Search for items with the same title.

Export reference: BibTeX RIS (EndNote, ProCite, RefMan) HTML/Text

Persistent link: https://EconPapers.repec.org/RePEc:ekd:010027:10376

Access Statistics for this paper

More papers in EcoMod2017 from EcoMod Contact information at EDIRC.
Bibliographic data for series maintained by Theresa Leary ().