Wavelet based long memory model for modelling wheat price in India

Abstract

Agricultural time-series data concerning production, prices, export and import of several agricultural commodities is published by Indian government along with other private agricultural sectors every year. The analysis of these factors is necessary to formulate and apply several policies regarding food acquisition and its distribution, quality and quantity of import and export products, pricing structure, MSP of agricultural commodities etc. Box - Jenkins's Autoregressive integrated moving average (ARIMA) model is broadly utilized in the field of time-series. In the field of time-series analysis, it is assumed by most of the researchers that the data points of different time lags do not depend on each other, i.e. absence of long memory process. But in agriculture, market price data exhibits that the observation are dependent on distant past. This is the possible indication of long memory process or long range dependency in the mean model. Autoregressive fractionally integrated autoregressive moving average (ARFIMA) model is generally used to portray the characteristic features of the long memory time series models as well as for the forecasting purposes. In this study wavelet decomposition is used for increasing the forecasting accuracy of the ARFIMA model. Daily wholesale data of wheat of Rewari market of Haryana for the period of January, 2010 to November, 2017 is used for the demonstration of our approach.

Keywords

• ARIMA
• ARFIMA
• Long memory
• Wavelet analysis
• Wheat price