{"paper_id":"2404.14136","title":"Elicitability and identifiability of tail risk measures","authors":["Tobias Fissler","Fangda Liu","Ruodu Wang","Linxiao Wei"],"paper_date":"2024-04-22","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2404.14136v3","page_url":"https://thequant.space/flowcharts/elicitability-and-identifiability-of-tail-risk-measures/","scores":{"empirical_rigor":2.5,"math_complexity":9.2,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper establishes joint identifiability and elicitability results for tail risk measures together with the corresponding quantile, and provides the tail expectile as an example.","quote":"This paper establishes joint identifiability and elicitability results of tail risk measures together with the corresponding quantile, provided that their generators are identifiable and elicitable, respectively. As an example, we establish the joint identifiability and elicitability of the tail expectile together with the quantile.","summary":"Tail risk measures are fully determined by the distribution of the underlying loss beyond its quantile at a certain level, with Value-at-Risk, Expected Shortfall and Range Value-at-Risk being prime examples. They are induced by law-based risk measures, called their generators, evaluated on the tail…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"The set A = {(VaR‑p(F), ρ(F)) : F ∈ M} has a simply connected interior.","type":"statistical","stated":"explicit","quote":"(i) Let A = {(VaR− p (F), ρ(F)) : F ∈M} ⊆R2 and suppose that the interior of A, int(A) is simply connected.","support":"full"},{"assumption":"The generator ρ* is identifiable with a strict M‑identification function that is locally bounded.","type":"statistical","stated":"explicit","quote":"(ii) The generator ρ∗is identifiable with a strict M-identification function Vρ∗: R2 →R, which is locally bounded.","support":"full"},{"assumption":"The expectation of the identification function V(v,x,·) with respect to any F ∈ M is continuously differentiable.","type":"statistical","stated":"explicit","quote":"(iii) The identification function V : R3 →R2 defined by V (v, x, y) =   1{y⩽v} −p 1{y>v}Vρ∗(x, y)   is such that its expectation with respect to any F ∈M is continuously differentiable.","support":"full"},{"assumption":"The expectation of the score S with respect to any F ∈ M is twice continuously differentiable.","type":"statistical","stated":"explicit","quote":"(iv) The expectation of the score S with respect to any F ∈M is twice continuously differen-tiable.","support":"full"}]},"datasets":{"status":"none_found","items":[],"known":[],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"none"},"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":"none","findings":[{"finding":"Joint identifiability and elicitability of tail risk measures are established, provided their generators are identifiable and elicitable.","kind":"theoretical","quote":"This paper establishes joint identifiability and elicitability results of tail risk measures together with the corresponding quantile, provided that their generators are identifiable and elicitable, respectively.","support":"full"},{"finding":"The tail expectile together with the quantile is shown to be jointly identifiable and elicitable.","kind":"theoretical","quote":"As an example, we establish the joint identifiability and elicitability of the tail expectile together with the quantile.","support":"full"},{"finding":"The resulting consistent scores form a novel class of weighted scores that nest the known class of scores for Expected Shortfall and the quantile.","kind":"theoretical","quote":"The corresponding consistent scores constitute a novel class of weighted scores, nesting the known class of scores of Fissler and Ziegel for the Expected Shortfall together with the quantile.","support":"full"},{"finding":"The main results connect identifiability or elicitability of a tail risk measure ρ with that of its generator ρ*, and provide explicit conversions between their identification and score functions.","kind":"theoretical","quote":"7 Concluding remarks Our main results in Sections 4 and 5 establish an intimate connection between identifiability or elicitability of a tail risk measure ρ and that of its generator ρ∗, as well as their identification functions and score functions.","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"available","supports":[],"contradicts":[],"qualifies":[],"compared_with":20,"citations":{"cited_by_in_corpus":2,"by_independent_authors":1,"how_cited":{"used_as_baseline":0,"uses_method_or_data":1,"extends":0,"discusses_findings":0,"mentions":0,"unclassified":1},"independent_papers":[{"paper":{"paper_id":"2505.04553","title":"Risk-sensitive Reinforcement Learning Based on Convex Scoring Functions","paper_date":"2025-05-07","authors":["Shanyu Han","Yang Liu","Xiang Yu"],"empirical_rigor":5,"page_url":"https://thequant.space/flowcharts/risk-sensitive-reinforcement-learning-based-on-convex-scoring-functions/"},"how":"uses_method_or_data","quote":null}],"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":2,"extracted_at":"2026-11-14T19:57:55Z"},"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/"}