Effectiveness of price forecasting techniques for capturing asymmetric volatility for onion in selected markets of Delhi

Abstract

Onion prices exhibit very high instability/volatility in all the selected markets of Delhi. The present study aimed to forecast the prices of onion for three markets of Delhi, viz. Azadpur, Keshopur and Shahdara using different foresting techniques. The study was based on times series secondary data on monthly wholesale price of onion from April 2005 to February 2015. After ensuring the stationarity of series after seasonal adjustment and differencing, the best ARIMA model was chosen for individual series. The residuals were checked for the presence of autocorrelation, it was found that the residuals are correlated implying improper specification of the models. Also, the plots of prices in the selected markets also exhibited nonlinearity in the series, which necessitated the application of non-linear models to the data. Considering this, squared residuals were checked for the presence of conditional heteroscedasticity. The presence of conditional heteroscedasticity was found in all the three price series. A significant ARCH-LM test and high value of skewness and kurtosis coefficients justify the selection of EGARCH models as the best fit models in these markets. The out-of-sample forecast of onion price has been carried out by using the best fitted EGARCH/GARCH model and it is projected that the prices of onion will be between rupees 1800-1950 per quintal in Azadpur and Shahdara market; while the prices will remain between rupees 2178 to 2413 per quintal in Keshopur market during March to July, 2015.

Keywords

• EGARCH model
• GARCH model
• Onion
• Onion prices
• Volatility