Time Varying Regime Transitions and Tail Risk Forecasting in Emerging Equity Markets: A Macro Conditional Markov Switching GARCH Analysis of NIFTY 50 Returns

Authors

https://doi.org/10.22105/tqfb.v3i2.84

Abstract

Tail risk in emerging equity markets does not arrive at a constant pace. It clusters around macroeconomic and geopolitical disturbances whose timing the conventional regime switching toolkit treats as exogenous to the model. We argue that this treatment is empirically untenable for the Indian equity market over the 2018 to 2025 window, a period dense with precisely datable shocks, and we replace it with a time varying transition probability Markov switching GARCH framework in which the probabilities of entering and exiting the high volatility regime depend on a parsimonious set of observable global and domestic risk drivers. Using 2039 daily observations of NIFTY 50 returns and four macro covariates spanning global risk appetite, currency pressure, domestic monetary stance, and foreign portfolio flows, we estimate the model through an augmented Hamilton filter with Student t innovations governing within regime persistence. The likelihood ratio test rejects the constant transition probability restriction with $p = 0.014$. The smoothed regime probabilities align with the March 2020 pandemic rupture, the 2022 Russia Ukraine episode, and the synchronized monetary tightening to a degree the constant probability comparator cannot reproduce. We push the model out of sample through rolling reestimation over 539 trading days and evaluate one day ahead Value at Risk and Expected Shortfall at the one percent and five percent levels using Kupiec unconditional coverage, Christoffersen conditional coverage, Engle and Manganelli dynamic quantile, and Acerbi and Szekely Expected Shortfall tests. The time varying specification delivers valid coverage at both confidence levels where the single regime Student t GARCH baseline is rejected by Kupiec at the one percent level and by three of the four tests at the five percent level, and where the constant probability Markov switching GARCH is rejected by the Acerbi and Szekely magnitude test at both levels. A decomposition of regime entry intensity attributes 63.0 percent of the variation to the United States VIX and 25.8 percent to the rupee depreciation rate. The exit intensity is dominated by domestic policy rate easing and the reversal of foreign outflows. Under the Basel internal models traffic light approach the proposed model spends 200 of 289 rolling windows in the green zone against 133 for the single regime baseline, with neither specification entering the red zone, which translates into measurable capital relief without prudential cost.

Keywords:

Markov switching GARCH, Value at Risk, Expected Shortfall, NIFTY 50

References

  1. [1] Acerbi, C., & Szekely, B. (2014a). Back-testing expected shortfall. Risk, 27, 76–81.
  2. [2] https://www.academia.edu/download/79535895/22aa9922-f874-4060-b77a-0f0e267a489b.pdf
  3. [3] Acerbi, C., & Szekely, B. (2017). General properties of backtestable statistics. Available at SSRN
  4. [4] https://papers.ssrn.com/sol3/Delivery.cfm?abstractid=2905109
  5. [5] Ang, A., & Bekaert, G. (2002). Regime switches in interest rates. Journal of Business and Economic
  6. [6] Statistics, 20 (2), 163–182. https://doi.org/10.1198/073500102317351946
  7. [7] Ardia, D. (2008). Financial risk management with Bayesian estimation of GARCH models. Springer.
  8. [8] https://doi.org/10.1007/978-3-540-78657-3
  9. [9] Ardia, D. (2009). Bayesian estimation of a Markov-switching threshold asymmetric GARCH model with
  10. [10] Student-t innovations. The Econometrics Journal, 12 (1), 105–126. https://doi.org/10.1111/j.1368-
  11. [11] X.2008.00268.x
  12. [12] Ardia, D., Bluteau, K., Boudt, K., & Catania, L. (2018). Forecasting risk with Markov-switching GARCH
  13. [13] models. International Journal of Forecasting, 34 (4), 733–747. https://doi.org/10.1016/j.ijforecast.2018.05.004
  14. [14] Augustyniak, M. (2014). Maximum likelihood estimation of the Markov-switching GARCH model. Computational
  15. [15] Statistics & Data Analysis, 76, 61–75. https://doi.org/10.1016/j.csda.2013.01.026
  16. [16] Bai, J., & Perron, P. (1998). Estimating and testing linear models with multiple structural changes.
  17. [17] Econometrica, 66 (1), 47–78. https://doi.org/10.2307/2998540
  18. [18] Bai, J., & Perron, P. (2003). Computation and analysis of multiple structural change models. Journal of
  19. [19] Applied Econometrics, 18 (1), 1–22. https://doi.org/10.1002/jae.659
  20. [20] Basel Committee on Banking Supervision. (1996). Supervisory framework for the use of "backtesting" in
  21. [21] conjunction with the internal models approach to market risk capital requirements. Bank for International Settlements.
  22. [22] Basel Committee on Banking Supervision. (2019). Minimum capital requirements for market risk. Bank for
  23. [23] International Settlements. https://www.bis.org/bcbs/publ/d457.htm?utm_source
  24. [24] Bauer, G. H., & Vorkink, K. (2015). Forecasting multivariate realized stock market volatility. Journal of
  25. [25] Econometrics, 187(1), 263–278. https://doi.org/10.1016/j.jeconom.2015.03.027
  26. [26] Bollerslev, T. (1986). Generalized autoregressive conditional heteroskedasticity. Journal of Econometrics,
  27. [27] (3), 307–327. https://doi.org/10.1016/0304-4076(86)90063-1
  28. [28] Cai, J. (1994). A Markov model of switching-regime ARCH. Journal of Business and Economic Statistics,
  29. [29] (3), 309–316. https://doi.org/10.1080/07350015.1994.10524546
  30. [30] Chen, S. S., Liu, J. W., & Wang, S. (2013). Regime-dependent hedging effectiveness in equity portfolios.
  31. [31] Journal of Banking and Finance, 37 (5), 1500–1515.
  32. [32] Christoffersen, P. F. (1998). Evaluating interval forecasts. International Economic Review, 39 (4), 841–862.
  33. [33] https://doi.org/10.2307/2527341
  34. [34] Costanzino, N., & Curran, M. (2015). Backtesting general spectral risk measures with application to
  35. [35] expected shortfall. Journal of Risk Model Validation, 9(1), 21–31. https://doi.org/10.21314/JRMV.2015.131
  36. [36] Dickey, D. A., & Fuller, W. A. (1979). Distribution of the estimators for autoregressive time series with a
  37. [37] unit root. Journal of the American Statistical Association, 74 (366), 427–431. https://doi.org/10.1080/0162
  38. [38] 1979.10482531
  39. [39] Diebold, F. X., Lee, J. H., & Weinbach, G. C. (1994). Regime switching with time-varying transition
  40. [40] probabilities. In C. Hargreaves (Ed.), Nonstationary time series analysis and cointegration (pp. 283–302).
  41. [41] Oxford University Press. https://www.torrossa.com/en/resources/an/5573303#page=160
  42. [42] Ding, Z., Granger, C. W. J., & Engle, R. F. (1993). A long memory property of stock market returns and a
  43. [43] new model. Journal of Empirical Finance, 1 (1), 83–106. https://doi.org/10.1016/0927-5398(93)90006-D
  44. [44] Engle, R. F. (1982). Autoregressive conditional heteroscedasticity with estimates of the variance of United
  45. [45] Kingdom inflation. Econometrica, 50 (4), 987–1008. https://doi.org/10.2307/1912773
  46. [46] Engle, R. F., & Manganelli, S. (2004). CAViaR: Conditional autoregressive value at risk by regression
  47. [47] quantiles. Journal of Business and Economic Statistics, 22 (4), 367–381. https://doi.org/10.1198/07350010
  48. [48] Escanciano, J. C., & Olmo, J. (2010). Backtesting parametric value at risk with estimation risk. Journal of
  49. [49] Business and Economic Statistics, 28 (1), 36–51. https://doi.org/10.1198/jbes.2009.07152
  50. [50] Filardo, A. J. (1994). Business-cycle phases and their transitional dynamics. Journal of Business and
  51. [51] Economic Statistics, 12 (3), 299–308. https://doi.org/10.1080/07350015.1994.10524545
  52. [52] Filardo, A. J., & Gordon, S. F. (1998). Business cycle durations. Journal of Econometrics, 85 (1), 99–123.
  53. [53] https://doi.org/10.1016/S0304-4076(97)00075-5
  54. [54] Ghosh, S., & Saha, R. (2017). Value at risk estimation with GARCH family models for Indian equity market.
  55. [55] Indian Journal of Finance, 11 (8), 7–23.
  56. [56] Gray, S. F. (1996). Modeling the conditional distribution of interest rates as a regime-switching process.
  57. [57] Journal of Financial Economics, 42 (1), 27–62. https://doi.org/10.1016/0304-405X(96)00875-6
  58. [58] Haas, M., Mittnik, S., & Paolella, M. S. (2004). A new approach to Markov-switching GARCH models.
  59. [59] Journal of Financial Econometrics, 2 (4), 493–530. https://doi.org/10.1093/jjfinec/nbh020
  60. [60] Hamilton, J. D. (1989). A new approach to the economic analysis of nonstationary time series and the
  61. [61] business cycle. Econometrica, 57 (2), 357–384. https://doi.org/10.2307/1912559
  62. [62] Hamilton, J. D., & Susmel, R. (1994). Autoregressive conditional heteroskedasticity and changes in regime.
  63. [63] Journal of Econometrics, 64 (1–2), 307–333. https://doi.org/10.1016/0304-4076(94)90067-1
  64. [64] Hansen, B. E. (1994). Autoregressive conditional density estimation. International Economic Review, 35 (3),
  65. [65] –730. https://doi.org/10.2307/2527081
  66. [66] Inclán, C., & Tiao, G. C. (1994). Use of cumulative sums of squares for retrospective detection of changes
  67. [67] of variance. Journal of the American Statistical Association, 89 (427), 913–923. https://doi.org/10.1080/01
  68. [68] 1994.10476841
  69. [69] Karmakar, M. (2005). Modeling conditional volatility of the Indian stock markets. Vikalpa, 30 (3), 21–38.
  70. [70] Kerkhof, J., & Melenberg, B. (2004). Backtesting for risk-based regulatory capital. Journal of Banking and
  71. [71] Finance, 28 (8), 1845–1865. https://doi.org/10.1016/j.jbankfin.2003.06.005
  72. [72] Kim, C. J. (1994). Dynamic linear models with Markov switching. Journal of Econometrics, 60 (1–2), 1–22.
  73. [73] https://doi.org/10.1016/0304-4076(94)90036-1
  74. [74] Kim, C. J., & Nelson, C. R. (1999). State space models with regime switching: Classical and Gibbs-sampling
  75. [75] approaches with applications. MIT Press. https://doi.org/10.2307/2669796
  76. [76] Klaassen, F. (2002). Improving GARCH volatility forecasts with regime-switching GARCH. Empirical
  77. [77] Economics, 27 (2), 363–394. https://doi.org/10.1007/s001810100100
  78. [78] Kumar, D., & Maheswaran, S. (2014). A regime-switching approach for modelling the volatility of emerging
  79. [79] market returns. Margin: The Journal of Applied Economic Research, 8 (1), 25–57. https://doi.org/10.1177/
  80. [80] Kupiec, P. H. (1995). Techniques for verifying the accuracy of risk measurement models. Journal of
  81. [81] Derivatives, 3 (2), 73–84. https://doi.org/10.3905/jod.1995.407942
  82. [82] Kwiatkowski, D., Phillips, P. C. B., Schmidt, P., & Shin, Y. (1992). Testing the null hypothesis of
  83. [83] stationarity against the alternative of a unit root. Journal of Econometrics, 54 (1–3), 159–178. https:
  84. [84] //doi.org/10.1016/0304-4076(92)90104-Y
  85. [85] Layton, A. P., & Smith, D. R. (2004). Recession dating using a Markov-switching approach. Journal of
  86. [86] Forecasting, 23 (6), 405–420.
  87. [87] Lo, M. C., & Piger, J. (2008). Is the response of output to monetary policy asymmetric? Evidence from a
  88. [88] regime-switching coefficients model. Journal of Money, Credit and Banking, 37 (5), 865–886.
  89. [89] https://www.jstor.org/stable/3839150
  90. [90] Lopez, J. A. (1999). Methods for evaluating value at risk estimates. Federal Reserve Bank of San Francisco
  91. [91] Economic Review, 2, 3–17. https://ideas.repec.org/a/fip/fedfer/y1999p3-17n2.html?utm_source
  92. [92] Mahajan, S., & Wagh, R. (2008). Regime switching analysis of the Indian stock market. Vikalpa, 33 (1),
  93. [93] –32.
  94. [94] McNeil, A. J., & Frey, R. (2000). Estimation of tail-related risk measures for heteroscedastic financial time
  95. [95] series: An extreme value approach. Journal of Empirical Finance, 7 (3–4), 271–300. https://doi.org/10.101
  96. [96] /S0927-5398(00)00012-8
  97. [97] Meinshausen, N. (2006). Quantile regression forests. Journal of Machine Learning Research, 7, 983–999.
  98. [98] Patton, A. J., Ziegel, J. F., & Chen, R. (2019). Dynamic semiparametric models for expected shortfall (and
  99. [99] value at risk). Journal of Econometrics, 211 (2), 388–413. https://doi.org/10.1016/j.jeconom.2019.01.017
  100. [100] Paul, A., & Sarkar, S. (2020). Quantile regression based value at risk for the Indian equity market. Indian
  101. [101] Economic Journal, 68 (3), 437–451. https://doi.org/10.1177/0019466220972939
  102. [102] Sanso, A., Arago, V., & Carrion, J. L. (2004). Testing for changes in the unconditional variance of financial
  103. [103] time series. Revista de Economia Financiera, 4, 32–53.
  104. [104] https://dspace.uib.es/xmlui/bitstream/handle/11201/152078/524035.pdf
  105. [105] Schwert, G. W. (1989). Why does stock market volatility change over time? Journal of Finance, 44 (5),
  106. [106] –1153. https://doi.org/10.1111/j.1540-6261.1989.tb02647.x
  107. [107] Schwert, G. W. (1990). Stock volatility and the crash of ’87. Review of Financial Studies, 3 (1), 77–102.
  108. [108] https://doi.org/10.1093/rfs/3.1.77
  109. [109] Srinivasan, P. (2010). Modeling and forecasting the stock market volatility of S&P 500 index using GARCH
  110. [110] models. IUP Journal of Behavioral Finance, 7 (1–2), 71–
  111. [111] https://search.proquest.com/openview/673b4f1f562f7e081b8f7bb1c08f0f8a/1?pqorigsite=
  112. [112] gscholar&cbl=54444
  113. [113] Tiwari, A. K., Aye, G. C., & Gupta, R. (2019). Stock market efficiency analysis using long spans of
  114. [114] data: A multifractal detrended fluctuation approach. Finance Research Letters, 28, 398–411. https:
  115. [115] //doi.org/10.1016/j.frl.2018.06.012
  116. [116] Tripathy, N., & Gil-Alana, L. A. (2010). Suitability of volatility models for forecasting stock market returns:
  117. [117] A study on the Indian National Stock Exchange. American Journal of Applied Sciences, 7 (11), 1487–1494.
  118. [118] https://doi.org/10.3844/ajassp.2010.1487.1494
  119. [119] Truong, C., Oudre, L., & Vayatis, N. (2020). Selective review of offline change point detection methods.
  120. [120] Signal Processing, 167, Article 107299. https://doi.org/10.1016/j.sigpro.2019.107299

Downloads

Published

2026-06-06

Issue

Vol. 3 No. 2 (2026): Transactions on Quantitative Finance and Beyond

Section

Articles

License

Copyright (c) 2026 Transactions on Quantitative Finance and Beyond

Creative Commons License

This work is licensed under a Creative Commons Attribution 4.0 International License.

How to Cite

Behera, J., Senapati, S., Panda, R., Sahoo, A., & Kalah, G. (2026). Time Varying Regime Transitions and Tail Risk Forecasting in Emerging Equity Markets: A Macro Conditional Markov Switching GARCH Analysis of NIFTY 50 Returns. Transactions on Quantitative Finance and Beyond, 3(2), 146-180. https://doi.org/10.22105/tqfb.v3i2.84
Crossref
Scopus
Google Scholar
Europe PMC

Similar Articles

1-10 of 16

You may also start an advanced similarity search for this article.