Randomized trial evaluates tail risk in Indian assets, suggesting superior predictions with EVT-Copula models.
This paper develops and validates a GARCH(1,1)–Extreme Value Theory (EVT)–Student-t Copula framework for three Indian asset classes, Nifty 50 (equities), Gold (INR), and USD/INR (currency),using 18 years of daily data spanning September 2007 to December 2025. Marginal tail distributions are modelled via Peaks-Over-Threshold Generalised Pareto Distribution (POF-GPD) fitted to GARCH-filtered residuals, while cross-asset dependence is captured using a Student-t copula estimated by maximum likelihood. The resulting EVT-Copula VaR and Expected Shortfall (ES) estimates are benchmarked against their Gaussian counterparts across three portfolio allocations, and the models are backtested against realised 2026 returns till April 2026.
No takes yet. Share an insight, caveat, or question.
Divya Grover (2026) studied this question.
Synapse has enriched 5 closely related papers on similar clinical questions. Consider them for comparative context: