Modelling and Forecasting the Volatility of Thin Emerging Stock Markets: The Case of Bulgaria

Abstract

Modern Portfolio Theory associates the stock market risk with volatility of the return. Volatility is measured by the variance of return but the investment community does not accepted this measure, since it weighs equally the deviations of the average return, while most investors determine the risk on the basis of small or negative returns. In the last few years the measure Value at Risk (VaR) has established itself in the practice. The issue about modelling and forecasting thin emerging stock markets risk is still open. The subject of the paper is the risk of the Bulgarian stock market. The aim of the paper is to give the investment community a model for assessment and forecasting of the Bulgarian stock market risk. The results of the research show that the SOFIX index has basic characteristics of most of the emerging stock markets, namely: high risk, significant autocorrelation, non-normality, volatility clustering. Three models have applied - RiskMetrics, EWMA with t distributed innovations and EWMA with GED distributed innovations. The EWMA with t distributed innovations and EWMA with GED distributed innovations adequately evaluate the risk of the Bulgarian stock market.

Keywords: Bulgarian stock market, volatility, EWMA, Value-at-Risk

JEL Classification: C22, G15