Evaluating correlation breakdowns in equity portfolio
Rautiainen, Mikko-Pekka (2005)
Kuvaus
Kokotekstiversiota ei ole saatavissa.
Tiivistelmä
The main purpose of this thesis is to investigate whether the correlations between stocks are stable. During periods of high market volatility, correlations between equity prices can differ substantially from those seen in quieter markets. This pattern is widely termed as correlation breakdown. Correlation breakdowns call into question the usefulness of managing the risk of equity portfolio based on correlations estimated from long time series of historical data, since they may be inaccurate precisely when they may be needed the most.
The correlation calculations are conducted with daily price data from 1993 to 2004 obtained from the Euronext Stock Exchange in Paris. Portfolio theory based equity diversification expects the correlations to be stable. The empirical results show that the correlation structure of the portfolio under investigation is not stable at all. The correlations between the stocks are clearly lower during the bullish market than during bearish market. It is also evidenced that in years 1999 and 2002, the years of lowest and highest standard deviations during the sample period, the correlations differed very much.
The results obtained from the empirical evaluations mean that diversification is not as good risk management tool for equity portfolio as the portfolio theory suggests. As the correlations between stocks are not stable as the theory expects them to be, they change just to the opposite direction that would be ideal. The correlations typically rise when the market crashes and sink when the market climbs.
The correlation calculations are conducted with daily price data from 1993 to 2004 obtained from the Euronext Stock Exchange in Paris. Portfolio theory based equity diversification expects the correlations to be stable. The empirical results show that the correlation structure of the portfolio under investigation is not stable at all. The correlations between the stocks are clearly lower during the bullish market than during bearish market. It is also evidenced that in years 1999 and 2002, the years of lowest and highest standard deviations during the sample period, the correlations differed very much.
The results obtained from the empirical evaluations mean that diversification is not as good risk management tool for equity portfolio as the portfolio theory suggests. As the correlations between stocks are not stable as the theory expects them to be, they change just to the opposite direction that would be ideal. The correlations typically rise when the market crashes and sink when the market climbs.