Statistical modelling for forecasting volatility in potato prices using ARFIMA-FIGARCH model

Abstract

This paper investigates the presence of long memory both in mean and volatility in the potato prices in Agra and Amritsar markets of India, using the Autoregressive fractionally integrated moving average (ARFIMA) and Fractionally integrated generalized autoregressive conditional heteroscedastic (FIGARCH) models. Long memory tests are carried out both for the returns and squared return series. The results of GPH estimator indicate the existence of long memory in the price data. The ARFIMA model with error following FIGARCH process is fitted to return prices of potato for each of the two markets. At the end, the forecasting performance of fitted ARFIMA-FIGARCH models are carried out in terms of RMAPE and RMSE and the residuals are also examined to check adequacy of the fitted models.