Volatility in Nigeria Financial markets the impact of Share index on Sustainable Economic Development in Nigeria. Hybrid Approach of GARCH-MIDAS, AND FIGARCH-MIDAS Regressions Models
- November 10, 2021
- Posted by: RSIS
- Categories: IJRIAS, Statistics
International Journal of Research and Innovation in Applied Science (IJRIAS) | Volume VI, Issue X, October 2021|ISSN 2454-6194
MU Bawa1, Dr. HG Dikko2, Dr. Anil Shabri3, Dr. J Garba4 and Dr. S Sadiku5
1Lecturer, Department of Mathematics, School of Science, Abubakar Tafawa Balewa University, Bauchi, Nigeria
2Reader Lecturer, Department of Statistics, Ahmadu Bello University, Zaria, Nigeria
3Associated professor, Department of Mathematics School of Science UTM Johor.
4Senior Lecturer, Department of Statistics, Ahmadu Bello University, Zaria, Nigeria
5Senior Lecturer, Department of Statistics, Ahmadu Bello University, Zaria, Nigeria
Abstracts: This Research considers the Comparison of forecasting performance between hybrid of GARCH-MIDAS and FIGARCH-MIDAS. The data employed for this study was secondary type in nature for all the variables and it is obtained from the publications of Central Bank of Nigerian bulletin, National Bureau of Statistics and World Bank Statistics Database dated, January ,2005 to Dec, 2019 for National Stock Exchange for all share index and seven macro-economic variables. Also, the result of ARCH-LM Test show that the presence of ARCH effects in the NSE series and Jarque- Bera Test indicated that the p-values for all variables are less than alpha level of significance (0.05). Hence, we would reject the null hypothesis that the data of all variables are normally distributed. Also, how we estimate the Fractional difference order, d, by Geweke and Porte-Hudak (GPH) method the results show that the value of d for the (NSE price) was found to be (0.043621) which falls within 0<d<0.5 indicating the presence of long-memory process of the data. The results show that based on the analysis of the table 6 above it is indicated that all variables have positive relationship with realized volatility except inflations rate that means increased in the variables can lead to attract more investor to invest in stock market with can be considered as a good proxy of the business cycle for the Economy development of Nigeria. Furthermore, based on the four models of the research we found that FIGARCH-MIDAS of forecast evaluations out- sample with shows that MSE (155.96) of RV+ PC have lest value than the remaining three models. Finally Based on the Table 38 we found that the models of RV+PC and PC are best models among the five models that’s FIGARCH-MIDAS are perform better than GARCH-MIDAS. With indicated the accommodated long memory with volatility are perform better than the model without long memory.
Key work: Volatility, FIGARCH, MIDAS, NATIONAL STOCK EXCHANGE and Hybrid.
