{"paper_id":"2505.05646","title":"Comparative Evaluation of VaR Models: Historical Simulation, GARCH-Based Monte Carlo, and Filtered Historical Simulation","authors":["Xin Tian"],"paper_date":"2025-05-08","paper_type":"empirical","paper_url":"https://arxiv.org/pdf/2505.05646v1","page_url":"https://thequant.space/flowcharts/comparative-evaluation-of-var-models-historical-simulation/","scores":{"empirical_rigor":6.5,"math_complexity":7,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes using the GARCH‑FHS method for risk management and 1‑week ahead forecasting.","quote":"We recommend the FHS method for practical applications in risk management, particularly in volatile market environments and high‑confidence settings.","summary":"This report presents a comprehensive evaluation of three Value-at-Risk (VaR) modeling approaches: Historical Simulation (HS), GARCH with Normal approximation (GARCH-N), and GARCH with Filtered Historical Simulation (FHS), using both in-sample and multi-day forecasting frameworks. We compute daily 5…","strategy":"GARCH-FHS"},"assumptions":{"status":"available","items":[{"assumption":"GARCH‑N relies on a Gaussian (normal) distribution for standardized residuals.","type":"model","stated":"explicit","quote":"GARCH‑N underestimates tail risk due to its reliance on the Gaussian assumption"},{"assumption":"Historical Simulation assumes a static historical return distribution.","type":"model","stated":"implied","quote":"the assumption of a static historical distribution becomes invalid"},{"assumption":"Return volatility is heteroskedastic, making identically distributed returns within the estimation window problematic.","type":"statistical","stated":"implied","quote":"if return volatility is heteroskedastic—as is often the case in financial markets—then assuming identically distributed returns within the estimation window is itself problematic"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"not_applicable","modeled":"n/a","headline_net_of_costs":null,"detail":null,"quote":null,"source":"front_matter","rule":"R3","candidates":{"front_matter":"n/a","evidence_card":"n/a","evidence_card_quoted":false},"meaning":"the paper reports no trading or execution result"},"results":{"status":"available","evaluation_type":"pricing-calibration","findings":[{"finding":"Historical Simulation and GARCH‑N show severe miscalibration with empirical breach rates far exceeding theoretical 5% and 1% levels.","kind":"performance","quote":"Our findings reveal severe miscalibration in the HS and GARCH‑N models, with empirical breach rates far exceeding theoretical levels at both 5% and 1% confidence thresholds."},{"finding":"Filtered Historical Simulation consistently aligns with theoretical expectations and shows desirable statistical and visual behavior.","kind":"performance","quote":"In contrast, the FHS method consistently aligns with theoretical expectations and exhibits desirable statistical and visual behavior."},{"finding":"GARCH‑N underestimates tail risk because of its Gaussian assumption.","kind":"negative","quote":"Results show that GARCH‑N underestimates tail risk due to its reliance on the Gaussian assumption"},{"finding":"GARCH‑FHS provides more robust and conservative tail estimates than GARCH‑N.","kind":"performance","quote":"whereas GARCH‑FHS provides more robust and conservative tail estimates"},{"finding":"GARCH‑FHS outperforms GARCH‑N for multi‑day VaR and Expected Shortfall estimation at extreme quantiles.","kind":"performance","quote":"Overall, the GARCH + FHS method outperforms GARCH + Normal in terms of accuracy and robustness for estimating multi‑day VaR and ES at extreme quantiles."}],"reported_performance":{"strategy":"GARCH-FHS","sharpe":null,"sharpe_benchmark":null,"annual_return_pct":null,"total_return_pct":null,"max_drawdown_pct":null},"out_of_sample":{"method":"unclear","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[{"paper":{"paper_id":"2409.18970","title":"Portfolio Stress Testing and Value at Risk (VaR) Incorporating Current Market Conditions","paper_date":"2024-09-12","authors":["Krishan Mohan Nagpal"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/portfolio-stress-testing-and-value-at-risk-var-incorporati/"},"question":"Do Gaussian‑based VaR methods underestimate tail risk compared to non‑Gaussian approaches?","this_paper_finding":"GARCH‑N underestimates tail risk because of its Gaussian assumption.","other_paper_finding":"Gaussian‑parametrized VaR is lower than Historical Simulation VaR for the 97.5% confidence level because the Gaussian distribution does not capture heavy tails.","other_paper_quote":"Gaussian distribution based VaR is lower than Historical Simulation VaR as Gaussian distribution does not capture the heavy tails of the distribution.","note":"Both find Gaussian‑based VaR is lower: A shows Gaussian VaR < Historical Simulation VaR at 97.5% confidence, and B shows GARCH‑N underestimates tail risk due to its Gaussian assumption.","confidence":0.808},{"paper":{"paper_id":"2409.18970","title":"Portfolio Stress Testing and Value at Risk (VaR) Incorporating Current Market Conditions","paper_date":"2024-09-12","authors":["Krishan Mohan Nagpal"],"empirical_rigor":6,"page_url":"https://thequant.space/flowcharts/portfolio-stress-testing-and-value-at-risk-var-incorporati/"},"question":"Which VaR method provides higher (more conservative) tail risk estimates?","this_paper_finding":"GARCH‑FHS provides more robust and conservative tail estimates than GARCH‑N.","other_paper_finding":"Gaussian‑parametrized VaR is lower than Historical Simulation VaR for the 97.5% confidence level because the Gaussian distribution does not capture heavy tails.","other_paper_quote":"Gaussian distribution based VaR is lower than Historical Simulation VaR as Gaussian distribution does not capture the heavy tails of the distribution.","note":"At 97.5% confidence Gaussian VaR is lower than Historical Simulation VaR, and GARCH‑FHS yields more robust tail estimates than GARCH‑N, both showing heavier‑tail approaches give larger VaR.","confidence":0.58}],"contradicts":[],"qualifies":[{"paper":{"paper_id":"2604.08765","title":"Reliability-Aware ETF Tail-Risk Monitoring","paper_date":"2026-04-09","authors":["Tenghan Zhong","Keyuan Wu"],"empirical_rigor":7.5,"page_url":"https://thequant.space/flowcharts/reliability-aware-etf-tail-risk-monitoring/"},"question":"Which VaR approach yields breach rates closest to the intended confidence level?","this_paper_finding":"Historical Simulation and GARCH‑N show severe miscalibration with empirical breach rates far exceeding theoretical 5% and 1% levels.","other_paper_finding":"The 252‑day historical VaR benchmark is conservative (breach rate 4.42%), whereas the EWMA‑normal benchmark remains under‑covered (5.75%).","other_paper_quote":"The 252‑day historical VaR benchmark is also conservative at 4.42%, whereas the EWMA‑normal benchmark remains under‑covered at 5.75%.","note":"A shows severe miscalibration (breaches far above 5%/1%); B shows 252‑day historical VaR is conservative at 4.42% while EWMA‑normal is under‑covered at 5.75%.","confidence":0.439}],"compared_with":52,"citations":{"cited_by_in_corpus":0,"by_independent_authors":0,"how_cited":{"used_as_baseline":0,"uses_method_or_data":0,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":0},"independent_papers":[],"scope":"Citations between papers in this corpus only; citations from outside it are not counted."}},"implementation":{"status":"available","public":false,"code_url":null,"note":"No repository presented by the authors as their own was found in the paper. Absence here is not proof that no code exists."},"replication":{"status":"none_found","card":null,"note":"No replication of this paper has been run by thequant.space yet."},"extraction":{"text_source":"fulltext","model":"openai/gpt-oss-120b","version":1,"extracted_at":"2026-11-14T17:38:47Z"},"provenance":{"claims":"Everything here is what the authors state in the paper. Nothing was re-run or reproduced by the platform.","quotes":"Assumptions, datasets, cost detail and findings were extracted by a language model. Every quote is verbatim paper text. Where an item has `support`, \"full\" means every figure in it appears in the quoted sentences and \"partial\" means a figure is stated elsewhere in the paper; items with a figure found nowhere in the paper were discarded.","datasets_known":"datasets.known lists well-known vendors and public datasets by a stable id, found by a dictionary over the full text where the sentence says the data is used; it is independent of the model and covers only names in the dictionary.","flags":"transaction_costs.modeled, results.evaluation_type and results.out_of_sample.method are platform classifications (structured-decision models); see https://thequant.space/score-guide/#penalty-flags","comparisons":"supports / contradicts / qualifies are a language model's reading of two papers' quoted findings, restricted to closely related papers that share no author. They are pointers to read, not verified replications, and coverage is partial.","implementation":"code_url is a repository the paper itself presents as its own (rule-scored, ambiguous cases judged by a model), checked for liveness when it was recorded."},"docs":"https://thequant.space/agents/"}