• Ashima Talwar
• Dr. C.K. Goyal

This study is aimed at identifying the best GARCH model for risk estimation of soybean price. Here GARCH model parameters are estimated using normal distribution, student-t distribution and Generalized error distribution (GED). For this study, the daily soybean price data of NCDEX from Indore market is taken up. The soybean price data for return series exhibits high kurtosis and volatility clustering. The characteristics of the data captured by all three error distributions improve the efficiency of the predictive model. The results demonstrate that volatility is highly persistent in the price data of the commodity. The result also suggested that the GARCH model with GED distribution satisfy the diagnostic phase and gives optimum accuracy measures for a future price estimation.

GARCH, Error distribution, Soybean, Forecasting, Volatility

"A study on volatility estimation in soybean price using GARCH model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org), ISSN:2349-5162, Vol.6, Issue 3, page no.307-315, March-2019, Available :http://www.jetir.org/papers/JETIRAI06045.pdf

"A study on volatility estimation in soybean price using GARCH model", International Journal of Emerging Technologies and Innovative Research (www.jetir.org | UGC and issn Approved), ISSN:2349-5162, Vol.6, Issue 3, page no. pp307-315, March-2019, Available at : http://www.jetir.org/papers/JETIRAI06045.pdf