A STATISTICAL ANALYSIS ON PRICE VOLATILITY AND MARKET INTEGRATION IN MAJOR DOMESTIC GROUNDNUT MARKETS 2361
Loading...
Date
2017-06
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
JUNAGADH
Abstract
Key words:Groundnut markets, ARIMA, tail behavior, Gaussian GARCH, forecasting, volatility, Johansen test, VECM.
The volatility and market integration analysis were carried out in major domestic groundnut marketsviz. Kurnool (Andhra Pardesh), Rajkot (Gujarat) and Villupuram (Tamil Nadu) from 1996-April to 2016-April by using various statistical models available in the time series literature. Volatility in these markets wereanalyzedby using the novel univariate autoregressive integrated moving-average (ARIMA) model and conditional heteroscedsatic GARCH model.As a preliminary, the Augmented Dickey-Fuller test were conducted and it detected the presence of unit root in the price series at levels for all the three markets and the stationary and invertible property of ARIMA model were also studied. The ARCH-LM test suggested building generalized autoregressive conditional heteroscedastic (GARCH) model for all the three series. The tail behaviour of the underlying series is also studied by fitting Student-t GARCH and Gaussian GARCH model. A comparatively study of the above fitted models has been done in terms of root mean square error (RMSE), mean absolute error (MAE) and mean absolute percentage error (MAPE). For the entire three markets Gaussian GARCH model outperformed the other two models in terms of forecasting accuracy. The persistence of volatility is also ascertained based on the ARCH and GARCH parameters of the fitted Gaussian GARCH models, where the volatility persistence is high in Rajkot markets has compared to other two markets.
The Market integration analyses were also carried out by using Engle-Granger bivariate co-integration test and Johansen multivariate co-integration test.These tests revealed long-run equilibrium between these markets and the causality test indicates the existence of feedback relationship between Kurnool and Rajkot, Kurnool and Villupuram market but there is a unidirectional relationship from Rajkot to Villupuram market, which indicate price transmission occur between the markets. The Vector Error Correction model (VECM) captured the short-run adjustment towards the long-run equilibrium between the markets and the adequacy of the fitted VECM is also checked. The lead-lag relationship based on VAR model supported the results of Granger causality test, since the estimated coefficients of the VAR model were found to be significant. Overall, the result implies that, in the domestic groundnut markets price transmission occur effectively and there was also a well infrastructure facility to meet the proper good allocation in the studied markets.
Description
Keywords
STATISTICS