Modeling fractional cointegration between high and low stock prices in Asian countries

Abstract

The present study analyzes the interrelationship among daily high and low stock market indices in some developing stock markets with the perspective of fractional integration and cointegration. The analysis is performed by applying fractionally cointegrated vector error correction models (FVECM) as they can explain the short-run and long-run dynamics of high and low stock prices simultaneously. This study employs daily stock market index data from six major Asian countries and finds that daily (log) highs and lows do follow a long-run relationship. We find very slow hyperbolic decay of autocorrelations in the range series for all observed stock prices, and this dependence supports the hypothesis of nonstationary volatility in some cases. Forecasted highs and lows based on the FVECM provide better forecasts than traditional models based on the MSE and MAE. The FVECM range forecasts also show better out of sample performance over the HAR and ARFIMA models fitted to the range series.