Paper: arXiv 2501.11164

Authors: Jaco Visagie

Abstract

Recorded option pricing datasets are not always freely available. Additionally, these datasets often contain numerous prices which are either higher or lower than can reasonably be expected. Various reasons for these unexpected observations are possible, including human error in the recording of the details associated with the option in question. In order for the analyses performed on these datasets to be reliable, it is necessary to identify and remove these options from the dataset. In this paper, we list three distinct problems often found in recorded option price datasets alongside means of addressing these. The methods used are justified using sound statistical reasoning and remove option prices violating the standard assumption of no arbitrage. An attractive aspect of the proposed technique is that no option pricing model-based assumptions are used. Although the discussion is restricted to European options, the procedure is easily modified for use with exotic options as well. As a final contribution, the paper contains a link to six option pricing datasets which have already been cleaned using the proposed methods and can be freely used by researchers.

Complexity vs Empirical Score

  • Math Complexity: 4.0/10
  • Empirical Rigor: 7.0/10
  • Quadrant: Street Traders — empirical and applied, lower math complexity

Why this score: The paper employs standard statistical reasoning and arbitrage bounds (equations 1 and 2) rather than advanced mathematical derivations, resulting in moderate complexity. However, it demonstrates high empirical rigor by providing specific datasets, details data sourcing (Yahoo Finance), specifies processing tools (Matlab), and outlines concrete cleaning steps ready for implementation.

Research Flowchart

  flowchart TD
  A["Research Goal: Clean Option Pricing Data"] --> B["Identify Three Problems"]
  B --> C["Apply Statistical Arbitrage Tests"]
  C --> D{"Price Violates No-Arbitrage?"}
  D -- Yes --> E["Flag as Outlier"]
  D -- No --> F["Retain Data Point"]
  E --> G["Outcome: Cleaned Datasets"]
  F --> G

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes a statistical technique for cleaning option price data that identifies and removes arbitrage violations and outliers without relying on option pricing model assumptions.

Source sentence
In this paper, we list three distinct problems often found in recorded option price datasets alongside means of addressing these. The methods used are justified using sound statistical reasoning and remove option prices violating the standard assumption of no arbitrage.

Assumes 6

  • Option prices must satisfy no‑arbitrage bounds for European calls and puts. model
    Source sentence
    The methods used are justified using sound statistical reasoning and remove option prices violating the standard assumption of no arbitrage.
  • All datasets share the same risk‑free interest rate, taken as the six‑month Treasury bill rate. market
    Source sentence
    Since all of these datasets are obtained at the same time and in the same market, the same risk free interest rate will be used for each dataset. We use the discount rate of Treasury bills in the secondary market as the risk free interest rate.
  • Dividend yields for all underlying assets are zero. market
    Source sentence
    As a result, the dividend rate is 0 for all underlying assets considered.
  • Residuals from the polynomial fit are i.i.d. normal with mean zero. statistical
    Source sentence
    Assume that the residuals are independently and identically 3 A statistical technique for cleaning option price data 450 500 550 600 650 700 750 0 50 100 150 Strike price Option price Figure 1: Google call option prices with the fitted second degree polynomial. distributed normal random variables with a mean of 0 and standard deviation of σ.
Show 2 more
  • Options are actively traded, so any arbitrage opportunity would be exploited immediately. market
    Source sentence
    Since the options considered are actively traded, it is reasonable to assume that these arbitrage opportu-nities would be exploited immediately.
  • The analysis is restricted to European call and put options. other
    Source sentence
    Regarding the type of option under consideration, we restrict our attention to European call and put options below.

Data

  • S&P 500 options dataset · Yahoo Finance options public
    11 May 2012 · S&P 500 index call and put options
    Source sentence
    The data used consist of European call and put option prices on the S&P 500 index, the PowerShares index and Google shares. On 11 May 2012 the S&P 500 index closed at $1353.39.
  • PowerShares index options dataset · Yahoo Finance options public
    11 May 2012 · PowerShares index call and put options
    Source sentence
    The PowerShares index is an index weighted by market capatilisation which consists of the largest non-financial companies the world over. On this day the PowerShares index closed at $64.18.
  • Google Inc. options dataset · Yahoo Finance options public
    11 May 2012 · Google stock call and put options
    Source sentence
    On the same date the share price of Google Inc. closed at $605.23. We obtained the prices of 545 call options and 532 put options on this stock from [3].

Costs

Not applicable The paper reports no trading or execution result.

Finds 5

  • For the S&P 500 dataset, 146 call options (25%) and 129 put options (17%) were removed during cleaning. statistical figure from elsewhere in the paper
    Source sentence
    This means that 146 call options and 129 put options were removed during the cleaning process, which corresponds to 25% and 17% of the original datasets, respectively.
  • For the PowerShares dataset, 29% of call options were removed. statistical
    Source sentence
    Turning our attention to the PowerShares dataset, we see that the data cleaning process reduces the number of call options from 413 to 293, which means that 29% of the options were removed.
  • For the PowerShares put options, 41% of the recorded options were removed. statistical
    Source sentence
    In this case 41% of the option prices are removed by cleaning.
  • For the Google dataset, call options were reduced by 5% and put options by 16% after cleaning. statistical
    Source sentence
    For the Google Inc. dataset, the number of call options is reduced from 545 to 519, constituting a 5% reduction in the number of options in the dataset. The number of options used is reduced by 16% in this instance.
  • The most extreme case required removal of 41% of recorded options to ensure realistic prices. statistical
    Source sentence
    In the most extreme case (that of the PowerShares put options), it was necessary to remove 41% of the recorded options in order to ensure that the prices are realistic.

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 11 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.

Cited References (94)

  1. A perfect calibration! Now what? (2004)
  2. Seasonal data cleaning for sales with chase demand strategy (2024)
  3. Exploratory D ata M ining and D ata C leaning (2003)
  4. Data C leaning: A P ractical P erspective (2013)
  5. Possibilistic data cleaning (2022)
  6. An improved algorithm for cleaning ultra high-frequency data (2010)
  7. Market C onsistency: M odel C alibration in I mperfect M arkets (2009)
  8. On the interchangeability of barrier option pricing models (2018)
and 86 more
  1. A note on the mean correcting martingale measure for geometric L 'evy processes (2011)
  2. The pricing of options and corporate liabilities (1973)
  3. On the range of option prices (1997)
  4. Martingales and stochastic integrals in the theory of continuous trading (1981)
  5. On the discrepancy between the objective and risk neutral densities in the pricing of E uropean options (2019)
  6. On parameter estimation in multi-parameter distributions (2018)
  7. Change of T ime and C hange of M easure (2006)
  8. Derivatives in F inancial M arkets with S tochastic V olatility (2001)
  9. Financial M odelling with J ump P rocesses (2004)
  10. Options, F utures, and O ther D erivatives, 7th ed. (2009)
  11. L'evy processes and I nfinitely D ivisible D istributions (2005)
  12. L'evy P rocesses in F inance: P ricing F inancial D erivatives (2003)
  13. The interpretation of interaction in contingency tables (1951)
  14. Galton, P earson, and the peas: a brief history of linear regression for statistics instructors (2001)
  15. Francis G alton’s account of the invention of correlation (1989)
  16. Sex bias in graduate admissions: data from B erkeley (1975)
  17. On an asymptotic relative efficiency concept based on expected volumes of confidence regions (2019)
  18. A new approach to goodness-of-fit testing based on the integrated empirical process (2000)
  19. A test for uniformity with unknown limits based on D ’ A gostino’s D (1990)
  20. An I ntroduction to C opulas (2006)
  21. Elementary S tatistical M ethods (2024)
  22. An I ntroduction to the B ootstrap (1994)
  23. A Primer for the Monte Carlo Method (1994)
  24. Monte C arlo M ethods (2020)
  25. Cours d’economie Politique, Vol. II. (1897)
  26. Pareto D istributions (2015)
  27. A review of goodness of fit tests for Pareto distributions (2019)
  28. Myopia and ambient night-time lighting (2000)
  29. A synopsis of the prevalence rates and environmental risk factors for myopia (2003)
  30. Myopia and ambient lighting at night (1999)
  31. Spurious C orrelations (2015)
  32. A new goodness of fit test for uniform distribution with censored observations (2021) — link
  33. Empirical properties of asset returns: s tylized facts and statistical issues (2001)
  34. The A rt of C omputer P rogramming (2011)
  35. Testing multivariate uniformity based on random geometric graphs (2020)
  36. Tests based on characterizations, and their efficiencies: A survey (2017) — link
  37. Linear forms and statistical criteria (1953 (in Russian), English translation in: Selected Transl. Math. Statist.and Prob. 3 (1963), 1–90.)
  38. Characterization of beta, binomial, and P oisson distributions (1991)
  39. Testing normality in any dimension by Fourier methods in a multivariate Stein equation (2020) — link
  40. Karl P earson and the correlation curve (1994)
  41. A new coefficient of correlation (2021)
  42. Tests for multivariate normality – a critical review with emphasis on weighted $ L ^2$-statistics (2020)
  43. On a new test of fit for the beta distribution (2020)
  44. New weighted $ L ^2$-type tests for the inverse G aussian distribution (2019) — link
  45. Ordinal measures of association (1958) — link
  46. Goodness-of-fit T echniques (1986)
  47. The A dvanced T heory of S tatistics (1967)
  48. Properties of powers of functions satisfying second-order linear differential equations with applications to statistics (2015) — link
  49. Models of antimicrobial pressure on intestinal bacteria of the treated host populations (2017)
  50. Fitting Beta Distributions Based on Sample Data (1994) — link
  51. Continuous univariate distributions (1995)
  52. The beta distribution – a physically consistent model for human exposure to airborne contaminants (2004) — link
  53. Random Nature of Soil Porosity and Related Properties (1989) — link
  54. Traffic flow and capacity of work sites on freeways (1991)
  55. Statistical inference for $ L ^2$-distances to uniformity (2018) — link
  56. Mathematical statistics : basic ideas and selected topics (2015)
  57. The limit distribution of weighted $ L ^2$-goodness-of-fit statistics under fixed alternatives, with applications (2017) — link
  58. Maple~2019 (2019)
  59. Asymptotic Theory of Certain “Goodness of Fit” Criteria Based on Stochastic Processes (1952)
  60. R: A Language and Environment for Statistical Computing (2021) — link
  61. A random variable related to the spacing of sample values (1950)
  62. Power studies of some tests for uniformity (1977)
  63. On the distribution and power of goodness-of-fit statistic with parametric and nonparametric applications (1987)
  64. Powerful goodness-of-fit tests based on the likelihood ratio (2002)
  65. uniftest: Tests for Uniformity (2015) — link
  66. PoweR : A Reproducible Research Tool to Ease M onte C arlo Power Simulation Studies for Goodness-of-fit Tests in R (2016)
  67. EDF statistics for goodness of fit and some comparisons (1974)
  68. A comparison of uniformity tests (2005)
  69. Asymptotic Results for Goodness-of-Fit Statistics with Unknown Parameters (1976) — link
  70. An approximation to the limit distribution of the E pps- P ulley test statistic for normality (1990)
  71. Tests concerning random points on a circle (1960)
  72. PearsonDS: Pearson Distribution System (2017) — link
  73. Continuous univariate distributions (1994)
  74. Fitting Equations to Data (1971)
  75. Robust regression and outlier detection (2005)
  76. Goodness-of-fit tests and minimum distance estimation via optimal transformation to uniformity (2009)
  77. Asymptotic Statistics (1998)
  78. Empirical processes with applications to statistics (1986)
  79. An Explicit Representation of a Stationary G aussian Process (1947)
  80. Stochastic Comparison of Tests (1960)
  81. Asymptotic Efficiency of Nonparametric Tests (1995)
  82. Bahadur efficiencies of the E pps– P ulley test for normality (2021) — link
  83. A test for uniformity with unknown limits based on d’ A gostino’s D (1990)
  84. A new approach to goodness-of-fit testing based on the integrated empirical process (2000)
  85. B usiness S tatistics using E xcel: A F irst C ourse for S outh A frican S tudents (2015)
  86. Elementary S tatistics: A S tep by S tep A pproach (2023)

0 of 94 cited works are in the corpus; resolved via arXiv source bundles, Semantic Scholar and OpenAlex. Corpus-wide: 2596 linked papers.