Forecasting Daily Volatility on Bucharest Stock Exchange using HAR Model

Abstract

In this paper we forecast realized volatility using a very liquid equity traded on Bucharest Stock Exchange, Property Fund (FP) which is a company that manages Romanian government real-estate properties and at that time had almost 40% market capitalization. Many research paper use strndard version of HAR model, with or without jumps to forecast volatility on markets with a high level of liquidity. Our result, based on Diebold an Mariano test show that forecast performance increase if we use a modified version of HAR model, allowing for average trade duration form prevoius day to play an important role in analysis.