{"paper_id":"2601.07991","title":"Optimal Option Portfolios for Student t Returns","authors":["Kyle Sung","Traian A. Pirvu"],"paper_date":"2026-01-12","paper_type":"theoretical","paper_url":"https://arxiv.org/pdf/2601.07991v1","page_url":"https://thequant.space/flowcharts/optimal-option-portfolios-for-student-t-returns/","scores":{"empirical_rigor":4,"math_complexity":9.5,"quadrant":"Lab Rats"},"proposes":{"status":"available","statement":"The paper proposes option portfolio optimization when underlying returns follow a skew‑elliptical t‑distribution, providing explicit portfolio weights for variance and a two‑term Cornish‑Fisher VaR approximation, and using numerical optimization for a three‑term VaR approximation.","quote":"This paper explores option portfolio optimization when the underlying returns are skew-elliptical t-distributed. We provide explicit portfolio weights for the variance and VaR approximation.","summary":"We provide an explicit solution for optimal option portfolios under variance and Value at Risk (VaR) minimization when the underlying returns follow a Student t-distribution. The novelty of our paper is the departure from the traditional normal returns setting. Our main contribution is the…","strategy":null},"assumptions":{"status":"available","items":[{"assumption":"Underlying asset returns are assumed to follow a skew‑elliptical t‑distribution.","type":"model","stated":"explicit","quote":"This paper explores option portfolio optimization when the underlying returns are skew-elliptical t-distributed. Though it is known that the skew-elliptical t-distribution better describes the behaviour of the underlying returns in the financial markets, to the best of our knowledge, the general question of the optimal options portfolio in this setting remains open. Contribution.","support":"full"},{"assumption":"After filtering with a GARCH(1,1) model, the residual returns (Zt) are assumed to be approximately i.i.d.","type":"statistical","stated":"explicit","quote":"Then, we use a GARCH(1, 1) model with Gaussian innovations to remove serial return dependence: that is, we fit α0, α1 and β1 such that the log returns Rt satisfy Rt = σtZt, where Z1, . . . are i.i.d. with Zt ∼N(0, 1) and where σt = α0 + α1R2 t−1 + β1σ2 t−1. We refer to Zt as the filtered return, and assume that the Zt are i.i.d. approximately.","support":"full"}]},"datasets":{"status":"available","items":[{"name":"Five Dow Jones Industrial Average stocks (DIS, XON, PFE, MO, INTC)","provider":"yfinance","kind":"market-prices","access":"public","period":"July 1 2002 to August 4 2005","universe":"Disney, Exxon Mobil, Pfizer, Altria Group, Intel","quote":"Following Hu and Kercheval (2010), we perform estimation using the closing prices for the same five stocks selected from the Dow Jones Industrial Average: Disney (DIS), Exxon Mobil (XON), Pfizer (PFE), Altria Group (MO), and Intel (INTC). Following the procedure outlined in Section 4, using the data between July 1 2002 and 4 August 2005, we convert the prices to daily log-returns, and drop the first 30 days, leaving","support":"full","known_id":"yahoo-finance"}],"known":[{"id":"yahoo-finance","name":"Yahoo Finance","provider":"Yahoo","kind":"market-prices","access":"public","quote":"Their source of the price data is not specified; we source our price data from yfinance (Aroussi, 2026).","mentions":1,"used_in":1}],"sample":{"start":null,"end":null,"market":null,"asset_class":null,"frequency":null},"data_resolution":"daily"},"transaction_costs":{"status":"none_found","modeled":"unclear","headline_net_of_costs":null,"detail":null,"quote":null,"source":"none","rule":"R0b","candidates":{"front_matter":"unclear","evidence_card":"no","evidence_card_quoted":false},"meaning":"no cost treatment was found in the passages the extractor read; that is not evidence that costs are not modeled"},"results":{"status":"available","evaluation_type":"unclear","findings":[{"finding":"Closed‑form expressions are derived for the optimal number of shares under variance minimization and the two‑term Cornish‑Fisher VaR approximation.","kind":"theoretical","quote":"We approximate the VaR with the Cornish-Fisher expansion, and in the case of two-terms, we find a closed-form expression for the optimal number of shares.","support":"full"},{"finding":"Numerical optimization yields optimal portfolios for the three‑term Cornish‑Fisher VaR approximation.","kind":"theoretical","quote":"We then use numerical optimization to compute the optimal portfolio for the case of the three-term Cornish-Fisher expansion.","support":"full"},{"finding":"Optimal CFVaR3 weights depart farther from variance‑based weights than CFVaR2 weights, especially under the skew‑t distribution.","kind":"performance","quote":"The CFVaR3 weights appear to depart farther from the variance than the CFVaR2 weights.","support":"full"},{"finding":"The effect of skewness on optimal weights is quantified by comparing skew‑t results with the standard Student‑t case; weights change noticeably when moving to the standard t distribution.","kind":"performance","quote":"The portfolio outlook changes when moving from the skew t distribution to the standard Student t distribution. 5.2.2. Our findings show that the optimal weights for the three-term expansion only departs more than the two-term-expansion from the variance weights in the case of the skew t distribution, showing that robust portfolios require consideration of skew distributions; this effect does not persist in the case","support":"full"}],"reported_performance":null,"out_of_sample":{"method":"none","headline_out_of_sample":null}},"independent_evidence":{"status":"none_found","supports":[],"contradicts":[],"qualifies":[],"compared_with":19,"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":2,"extracted_at":"2026-11-14T19:44:12Z"},"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/"}