Stochastic Volatilities and Correlations, Extreme Values and Modeling the Macroeconomic Environment, Under Which Brazilian Banks Operate
Marcos Souto and
Theodore Barnhill
No 2007/290, IMF Working Papers from International Monetary Fund
Abstract:
Using monthly data for a set of variables, we examine the out-of-sample performance of various variance/covariance models and find that no model has consistently outperformed the others. We also show that it is possible to increase the probability mass toward the tails and to match reasonably well the historical evolution of volatilities by changing a decay factor appropriately. Finally, we implement a simple stochastic volatility model and simulate the credit transition matrix for two large Brazilian banks and show that this methodology has the potential to improve simulated transition probabilities as compared to the constant volatility case. In particular, it can shift CTM probabilities towards lower credit risk categories.
Keywords: WP; FX rate; normal distribution; time series; Forecasting; stochastic volatility; fat-tail distributions; Monte Carlo estimation; Br rate; Wilk-Shapiro statistics; standard deviation; covariances model; Oil; Gold; Credit risk; Credit (search for similar items in EconPapers)
Pages: 52
Date: 2007-12-01
References: View references in EconPapers View complete reference list from CitEc
Citations: View citations in EconPapers (1)
Downloads: (external link)
http://www.imf.org/external/pubs/cat/longres.aspx?sk=21502 (application/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:imf:imfwpa:2007/290
Ordering information: This working paper can be ordered from
http://www.imf.org/external/pubs/pubs/ord_info.htm
Access Statistics for this paper
More papers in IMF Working Papers from International Monetary Fund International Monetary Fund, Washington, DC USA. Contact information at EDIRC.
Bibliographic data for series maintained by Akshay Modi ().