{"paper_id":"2408.06661","title":"The Efficient Tail Hypothesis: An Extreme Value Perspective on Market Efficiency","authors":["Junshu Jiang","Jordan Richards","Raphaël Huser","David Bolin"],"paper_date":"2024-08-13","paper_type":"survey-review","paper_url":"https://arxiv.org/pdf/2408.06661v3","page_url":"https://thequant.space/flowcharts/the-efficient-tail-hypothesis-an-extreme-value-perspective/","scores":{"empirical_rigor":6,"math_complexity":8.5,"quadrant":"Holy Grail"},"proposes":{"status":"available","statement":"The paper proposes a directional tail dependence (DTD) measure and the Efficient Tail Hypothesis (ETH) as an analogue of market efficiency for extreme events, along with estimators and testing methods.","quote":"we construct regular variation models on the entirety of \\mathbb{R}^d and develop a bivariate measure for asymmetry in the strength of extremal dependence between adjacent orthants. Our directional tail dependence (DTD) measure allows us to define the Efficient Tail Hypothesis (ETH) -- an analogue of the Efficient Mark","summary":"In econometrics, the Efficient Market Hypothesis posits that asset prices reflect all available information in the market. Several empirical investigations show that market efficiency drops when it undergoes extreme events. Many models for multivariate extremes focus on positive dependence, making…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Random vectors are regularly varying on all orthants of \\mathbb{R}^p.","type":"model","stated":"explicit","quote":"We consider random vectors, X := (X1, . . . , Xp)⊤∈Rp, that are regularly-varying"},{"assumption":"Marginal distributions are standardized to unit scale for balanced regular variation.","type":"model","stated":"explicit","quote":"Focusing on dependence modeling, we standardize the marginal distributions and derive mass balance constraints for these vectors to construct, without loss of generality"},{"assumption":"The Efficient Tail Hypothesis corresponds to zero directional tail dependence between information variables and future returns.","type":"statistical","stated":"explicit","quote":"define the Efficient Tail Hypothesis (ETH), a new concept analogous to the Efficient Market Hypothesis, which corresponds to the situation where λ(Xi, Yj) = 0 for i = 1, . . . , p"}]},"datasets":{"status":"available","items":[{"name":"High-frequency China derivatives dataset","provider":"six major exchanges in mainland China (SHFE, INE, CFFEX, CZC","kind":"order-book","access":"public","period":"2022-08-01 to 2023-07-31","universe":"commodity future derivatives (most actively traded instrument per product)","quote":"The data spans a year, from 2022-08-01 to 2023-07-31, incorporating all products from the six aforementioned exchanges, except CFFEX."}],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"intraday-bars"},"transaction_costs":{"status":"available","modeled":"no","headline_net_of_costs":null,"detail":null,"quote":"under the ideal situation where the trading cost is not considered","source":"front_matter","rule":"R3","candidates":{"front_matter":"no","evidence_card":"no","evidence_card_quoted":true},"card_detail":null,"card_quote":"under the ideal situation where the trading cost is not considered","meaning":"a trading or execution result is reported without costs"},"results":{"status":"available","evaluation_type":"trading-pnl","findings":[{"finding":"The Efficient Tail Hypothesis is rejected for China’s futures market at a 0.01 significance level.","kind":"statistical","quote":"Our empirical results suggest that the Efficient Tail Hypothesis (ETH) for China’s futures market is rejected under a significance level of α∗= 0.01."},{"finding":"A trading strategy based on tail‑inefficient assets yields significant overall excess returns in out‑of‑sample backtests.","kind":"performance","quote":"Our backtesting on out-of-sample data suggests that our trading strategy using tail-inefficient assets is profitable (under the ideal situation where the trading cost is not considered), which gives evidence against the Efficient Market Hypothesis."},{"finding":"Negative extreme depreciation is more influential than positive extreme events in driving tail inefficiency.","kind":"statistical","quote":"A deeper analysis of those tail-inefficient assets shows that negative extreme depreciation is more influential than positive extreme events."}],"reported_performance":null,"out_of_sample":{"method":"holdout","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":10,"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":true,"code_url":"https://github.com/junshujiang/tailEfficientTest","note":null},"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":"2026-11-14T18:04:14Z"},"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/"}