STATISTICAL PROPERTIES AND FORECASTING PERFORMANCE OF MARKOV-SWITCHING GARCH MODELS:A COMPARISON OF SINGLE-STAGE AND TWO-STAGE ESTIMATION APPROACHES
DOI:
https://doi.org/10.60787/tnamp.v25.721Keywords:
MS-GARCH, Single-Stage Optimization, two-Stage Optimization, Asymptotic Efficiency, Error PropagationAbstract
This paper evaluates and compares the forecasting performance of single-stage and two-stage Markov-Switching GARCH (MS-GARCH) models for forecasting the volatility of the Nigerian Stock Index using monthly data for the period January 2000-December 2025. Two different distributions are used to estimate the models: Gaussian and Student’s t. Model selection and forecast evaluation criteria include the log-likelihood value, AIC, BIC, RMSE, MAE, MAPE and QLIKE. Results show evidence of significant regime switching and that the Student’s t distribution is preferred over the Gaussian distribution. More importantly, we find that singlestage MS-GARCH model yields a more accurate and robust in-sample and out-ofsample forecast than two-stage MS-GARCH model. This study enriches the literature by demonstrating evidence that joint estimation enhances volatility forecasting in an emerging economy. The results support the application of the single-stage MS-GARCH(1,1) model for financial risk management, portfolio diversification and market surveillance in Nigeria.
Downloads
References
. Adegboyo, O. S., & Sarwar, K. (2025). Modelling and forecasting of Nigeria stock market volatility. Future Business Journal, 11(1), 124. https://doi.org/10.1186/s43093-025-00536-4, 1-13.
. Ardia, D., Bluteau, K., Boudt, K., & Trottier, D. A. (2019). Markov-switching GARCH models in R: The MSGARCH package. Journal of Statistical Software, 91(4), 1–38.
. Bauwens, L., Preminger, A., & Rombouts, J. V. K. (2010). Theory and inference for a Markovswitching GARCH model. Econometrics Journal, 13(2), 218–244.
. Blazsek, S., Kong, D., & Shadoff, S. R. (2024). Observable or latent Markov chains for scoredriven regime-switching volatility? Applied Economics, 57(52), 8693–8709.
. Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics, 31(3), 307–327.
. Emenike, K. O. (2010). Modelling stock returns volatility in Nigeria using GARCH models. Studies in Economics and Finance, 27(1), 27–41.
. Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United Kingdom inflation. Econometrica, 50(4), 987–1007.
. Fama, E. F. (1970). Efficient capital markets: A review of theory and empirical work. Journal of Finance, 25(2), 383–417.
. Haas, M., Mittnik, S., & Paolella, M. S. (2004). A new approach to Markov-switching GARCH models. Journal of Financial Econometrics, 2(4), 493–530.
. Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the business cycle. Econometrica, 57(2), 357–384. https://doi.org/10.2307/1912559
. Hotta, L. K., Trucíos, C., Pereira, P. L. V., & Zevallos, M. (2024). Forecasting VaR and ES through Markov Switching GARCH Models: Does the Specification Matter?, DOI: 10.2139/ssrn.4734361, 10–12
. Koch, D., Jeleskovic, V., & Younas, Z. I. (2024). Modelling and Predicting the Conditional Variance of Bitcoin Daily Returns: Comparison of Markov Switching GARCH and Stochastic Volatility Model, Papers 2401.03393, arXiv.org. 1-30.
. Korkpoe, C. H., & Howard, N. (2019). Volatility model choice for Sub-Saharan frontier equity markets: A Markov regime-switching Bayesian approach. Emerging Markets Journal, 9(1), 69–79. https://doi.org/10.5195/emaj.2019.172
. Pajor, A., Wróblewska, J., Kwiatkowski, Ł., & Osiewalski, J. (2024). Hybrid SV-GARCH, tGARCH and Markov-switching covariance structures in VEC models—Which is better from a predictive perspective? International Statistical Review, 92, 62–86.
. Pallotta, A., & Ciciretti, V. (2024). Should you use GARCH models for forecasting volatility? A comparison to GRU neural networks. Studies in Nonlinear Dynamics & Econometrics, 28(5), 725–738.
. Umar, Y. H., & Adeoye, M. (2020). A Markov regime switching approach of estimating volatility using Nigerian stock market data. American Journal of Theoretical and Applied Statistics, 9(4), 112–119. https://doi.org/10.11648/j.ajtas.20200904.11.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 The Transactions of the Nigerian Association of Mathematical Physics
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
