The Measurement Problem

Fat Tails, Estimation, and What Standard Finance Gets Wrong

Author
Affiliation

Jean-Marc Choufani

Independent Researcher

Published

2026

Preface

This is a working monograph. It is incomplete by design — new chapters are added as the research develops. Every version is dated. Errors, when found, are corrected in place and noted in the session log.

0.1 What this book argues

Standard financial methodology is built on assumptions that break quietly under fat-tailed return distributions. The breakdowns are not exotic edge cases — they occur at tail exponents routinely observed in real equity data (α ≈ 2–3). Each chapter of this book isolates one such breakdown, states the mathematical condition under which it occurs, and quantifies its empirical consequence using a panel of 106,163 stock-month observations across 715 U.S. equities from 2009 to 2025.

The through-line is epistemological: the method you choose determines what you can see, and the standard toolkit was not designed with fat tails in mind. This does not mean the standard toolkit is always wrong — it means there is an identifiable class of problems for which it systematically misleads, and that class is larger than commonly acknowledged.

0.2 Four central claims

  1. The Hill estimator’s domain of validity is narrower than its use implies. Applied to equity returns driven by discrete binary events (regulatory decisions, clinical trial readouts), it is inconsistent for the structural tail exponent. The consequence is systematic misclassification within the Taleb (2025) taxonomy.

  2. Newey-West HAC standard errors address one of two distinct problems introduced by overlapping windows. They correct serial correlation inflation. They do not correct directional bias in the point estimate — a separate problem that is amplified, not attenuated, by fat-tailed return distributions.

  3. The ergodicity deficit, as formalized by Peters (2019), has not been calibrated to empirically estimated tail exponents. The standard formula (σ²/2) is undefined for α ≤ 2 and mis-specified for α ∈ (2, 3). The empirical consequence for long-horizon compound growth has not been quantified across tail classes.

  4. The minimum track record required to distinguish skill from luck is a function of the tail exponent of the underlying return distribution. At α̂ = 2.69 — the median for U.S. equities in this sample — the required track record is substantially longer than Gaussian theory implies, with implications for how investment performance should be evaluated.

0.3 Who this is for

Anyone willing to think carefully about probability and measurement. The mathematics is precise but the motivation is accessible: these are questions about what we can and cannot know from the data we have, under the distributional conditions that actually obtain.

0.4 On the author

I am an orthodontist. I have no institutional affiliation in finance or mathematics. This work is guided entirely by curiosity and by a commitment to getting the mathematics right. Every substantive claim has been subjected to adversarial verification — an attempt to refute it before publishing it. Where the verification found errors, the errors are documented and the corrections noted.

Independent inquiry has a long tradition in quantitative research. What matters is whether the argument is correct, not whether the author holds the right credentials. Readers who find errors are encouraged to open an issue on the GitHub repository.

0.5 How to cite

Choufani, J.-M. (2026). The Measurement Problem: Fat Tails, Estimation, and What Standard Finance Gets Wrong (working monograph). Retrieved from [URL].

Individual chapters have separate SSRN preprint identifiers where available; these are listed at the top of each chapter.

0.6 License

This work is released under CC BY 4.0. You may share and adapt the material for any purpose, provided appropriate credit is given. No permission is needed to read, share, or build on this work.

First chapter written: 2026. This version: 2026.