Econometric Modelling: Testing of Randomness, Volatility, Casualty and Cointegration of Emerging Stock Market Indices of India and MIST Countries
R.Sivarethinamohan1, S.Sujatha2
1Dr. R. Sivarethinamohan, Chist Deemed To Be University, Bangalore (Karnataka), India.
2Dr. S. Sujatha, K. Ramakrishnan College of Technology, Tiruchirappalli (Tamil Nadu), India.
Manuscript received on November 15, 2019. | Revised Manuscript received on 20 November, 2019. | Manuscript published on December 10, 2019. | PP: 1402-1417 | Volume-9 Issue-2, December 2019. | Retrieval Number: A4946119119/2019©BEIESP | DOI: 10.35940/ijitee.A4946.129219
Open Access | Ethics and Policies | Cite | Mendeley | Indexing and Abstracting
© The Authors. Blue Eyes Intelligence Engineering and Sciences Publication (BEIESP). This is an open access article under the CC-BY-NC-ND license (http://creativecommons.org/licenses/by-nc-nd/4.0/)
Abstract: In general, stock market indices are widely interrelated to the other global markets to detect the impact of diversification opportunities. The present research paper empirically examines randomness and long term equilibrium affiliation amongst the emerging stock market of India and Mexico, Indonesia, South Korea and Turkey from the monthly time series data during February 2008 to October 2019. The researcher employs by the way, Run test, Pearson’s correlation test, Johnsen’s multivariate cointegration test, VECM and Granger causality test with reference to post-September 2008 Global financial crisis. The test results of the above finds that Nifty 50 and BSE Sensex is significantly cointegrated either among themselves or with MIST countries particularly during the post-September Global financial crisis. No random walk is found during the study period. The ADF (Augmented DickeyFuller) and PP (Phillips Pearson) tests evidenced stationarity at the level, but converted into non-stationarity in first difference. Symmetric and asymmetric volatility behaviors are studied using GARCH, EGARCH and TARCH models in order to test which model has the best forecasting ability. Leverage effect was apparent during the study period. So the influx of bad news has a bigger shock or blow on the conditional variance than the influx of good news. The residual diagnostic test (Correlogram-Squared residuals test, ARCH LM test and Jarque-Bera test) confirms GARCH (1,1) as the best suited model for estimating volatility and forecasting stock market index.
Keywords: Equilibrium, leverage Effects, Volatility Clustering, Asymmetric Effect, Cointegration, Causality, Random Walk, Persistence
Scope of the Article: Clustering