Modelling price volatility in onion using wavelet based hybrid models

The performance of wavelet-based hybrid models using different combinations of wavelet filters was compared to that of other conventional models to model volatility in the onion prices and arrivals at the Lasalgaon market of Maharashtra, which is known to be one of the largest markets in terms of arrivals. Monthly data of more than twenty-three years from 1996 onwards were taken into account. The results of hybrid models were compared to that of the ARIMA model. A normality test was conducted for both data series, and both of them were found to be non-normal. Therefore, a suitable nonparametric approach, namely wavelet decomposition of the data, was called for. For the price data, too, the wavelet-GARCH model with LA8 filter at five-level decomposition performed best for single value forecast, whereas the ARIMA performed well at expanded horizons. For the arrivals data, the Wavelet-GARCH model with LA8 filter at four level decomposition outperformed all models for single value forecasts. However, the wavelet-ANN model was able to perform better as the horizon expanded to twelve months. The study concluded that the wavelet hybrid models do pretty well for single value forecast, but as the horizon expands, the accuracy of the models decreases