pith. sign in

arxiv: 2606.23596 · v3 · pith:FEIEZKRWnew · submitted 2026-06-22 · 💱 q-fin.GN

Anatomy of the Market: A Body-Tail Test of Factor Models

Useong Shin This is my paper

Pith reviewed 2026-06-29 04:42 UTC · model grok-4.3

classification 💱 q-fin.GN
keywords factor modelspricing errorsmarket decompositionbody-tail teststochastic discount factorSharpe ratioq5 modelCRSP portfolio
0
0 comments X

The pith

Only the q5 model produces systematic offsetting alphas between the body and tail legs of the market portfolio.

A machine-rendered reading of the paper's core claim, the machinery that carries it, and where it could break.

The paper splits the investible CRSP market portfolio into dynamic value-weighted body and tail legs that add back exactly to the market return. It then checks whether common factor models that price the full market can still leave pricing errors in one leg that cancel in the other. Every model satisfies the overall recombination identity, yet only q5 shows negative alphas in the body and positive alphas in the tail while also falling short of its own market-only benchmark. Matched random splits of the same market do not generate this pattern.

Core claim

In an ideal stochastic discount factor, zero pricing errors and the maximum Sharpe ratio coincide; in a low-dimensional approximation they need not. The body-tail decomposition isolates this separation: the recombination identity holds for every model, while only q5 leaves systematic offsetting leg alphas and falls below its market-only baseline, despite dominating on spanning tests.

What carries the argument

Dynamic value-weighted body and tail legs of the CRSP market portfolio that recombine exactly to the market return.

If this is right

  • All models pass the aggregate recombination identity even when leg alphas are nonzero.
  • Only q5 exhibits the systematic negative-body and positive-tail alpha pattern.
  • q5 underperforms its market-only baseline on the body-tail test despite strong spanning performance.
  • The offsetting pattern disappears under matched random splits of the market.

Where Pith is reading between the lines

These are editorial extensions of the paper, not claims the author makes directly.

  • Standard spanning tests may overlook pricing discrepancies that appear only when the market is split by size or tail exposure.
  • The body-tail test could be applied to other benchmark portfolios to check whether the q5 pattern is market-specific.

Load-bearing premise

The body-tail split of the market portfolio isolates a meaningful separation between zero pricing errors and maximum Sharpe ratio that is not created by the splitting procedure itself.

What would settle it

If random splits of the market portfolio produce the same offsetting alpha pattern for q5, the body-tail result would be an artifact of the decomposition method.

Figures

Figures reproduced from arXiv: 2606.23596 by Useong Shin.

Figure 3.1
Figure 3.1. Figure 3.1: CRSP-based market return and standard market factors [PITH_FULL_IMAGE:figures/full_fig_p010_3_1.png] view at source ↗
Figure 3.1
Figure 3.1. Figure 3.1: CRSP-based market return and standard market factors [PITH_FULL_IMAGE:figures/full_fig_p007_3_1.png] view at source ↗
read the original abstract

In an ideal stochastic discount factor, zero pricing errors and the maximum Sharpe ratio coincide; in a low-dimensional approximation they need not. I study this separation by decomposing an investible CRSP market portfolio into dynamic value-weighted body and tail legs that recombine to the market return. All models pass the aggregate benchmark, and the recombination identity does not require zero leg alphas. Yet the identity holds for every model, while only q5 leaves systematic offsetting leg alphas-negative in the body, positive in the tail-and falls below its market-only baseline, despite dominating on spanning. Matched random splits remove the pattern.

Editorial analysis

A structured set of objections, weighed in public.

Desk editor's note, referee report, simulated authors' rebuttal, and a circularity audit. Tearing a paper down is the easy half of reading it; the pith above is the substance, this is the friction.

Referee Report

1 major / 0 minor

Summary. The manuscript decomposes the investible CRSP market portfolio into dynamic value-weighted body and tail legs that recombine exactly to the market return. It reports that all tested factor models satisfy the aggregate benchmark and the recombination identity (which does not require zero leg alphas), yet only q5 produces systematic offsetting leg alphas (negative in the body, positive in the tail), underperforms its market-only baseline despite strong spanning results, and that this pattern vanishes under matched random splits.

Significance. If the central empirical pattern holds after details are supplied, the body-tail test supplies a new diagnostic that separates models by their behavior across the market return distribution in a way that standard spanning tests do not capture. The explicit recombination identity plus the random-split control directly address whether the observed separation is an artifact of the decomposition procedure itself.

major comments (1)
  1. [Abstract] Abstract: the results for q5 and other models are stated without any information on estimation methods, statistical tests, sample periods, or the precise construction of alphas, making it impossible to evaluate whether the reported offsetting pattern is supported by the data.

Simulated Author's Rebuttal

1 responses · 0 unresolved

We thank the referee for highlighting the need for greater transparency in the abstract. We agree that the current abstract is too condensed to allow full evaluation of the empirical claims and will revise it accordingly.

read point-by-point responses

  1. Referee: [Abstract] Abstract: the results for q5 and other models are stated without any information on estimation methods, statistical tests, sample periods, or the precise construction of alphas, making it impossible to evaluate whether the reported offsetting pattern is supported by the data.

    Authors: We agree with this assessment. The abstract reports the central pattern (offsetting leg alphas only for q5, recombination identity holding for all models, and disappearance under random splits) but omits the supporting methodological details. In the revised manuscript we will expand the abstract to state: (i) the 1963–2022 CRSP sample with monthly frequency, (ii) dynamic value-weighted body-tail decomposition that exactly recombines to the market return, (iii) alpha estimation via time-series regressions of leg returns on the factor-model factors, and (iv) use of Newey–West standard errors for inference. These additions will allow readers to assess the statistical support for the q5 result directly from the abstract while preserving its brevity. revision: yes

Circularity Check

0 steps flagged

No significant circularity

full rationale

The paper's core claim rests on an explicit decomposition of the CRSP market into dynamic value-weighted body and tail legs that recombine exactly to the market return by construction; the text states this identity holds for all models and does not require zero leg alphas. The distinguishing result (systematic offsetting alphas only for q5, removed by matched random splits) is an empirical pattern tested against a control that directly addresses whether the split itself creates the separation. No equations reduce a fitted parameter or prediction to the same data by construction, no self-citation chain is load-bearing for the uniqueness of the result, and no ansatz or renaming of known results is invoked. The derivation is therefore self-contained against the recombination identity and the random-split benchmark.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Only the abstract is available; no free parameters, axioms, or invented entities can be extracted.

pith-pipeline@v0.9.1-grok · 5617 in / 1034 out tokens · 42047 ms · 2026-06-29T04:42:25.021210+00:00 · methodology

Review history (2 revisions) →

discussion (0)

Sign in with ORCID, Apple, or X to comment. Anyone can read and Pith papers without signing in.

Reference graph

Works this paper leans on

26 extracted references · 20 canonical work pages · 1 internal anchor

  1. [1]

    R., Ross, S

    Gibbons, M. R., Ross, S. A., & Shanken, J. (1989). A test of the efficiency of a given portfolio. Econometrica, 57(5), 1121--1152. https://www.jstor.org/stable/1913625

    arXiv 1989

  2. [2]

    W., & MacKinlay, A

    Lo, A. W., & MacKinlay, A. C. (1990). Data-snooping biases in tests of financial asset pricing models. The Review of Financial Studies, 3(3), 431--467. https://doi.org/10.1093/rfs/3.3.431

    work page doi:10.1093/rfs/3.3.431 1990

  3. [3]

    P., & Jagannathan, R

    Hansen, L. P., & Jagannathan, R. (1997). Assessing specification errors in stochastic discount factor models. The Journal of Finance, 52(2), 557--590. https://doi.org/10.1111/j.1540-6261.1997.tb04813.x

    work page doi:10.1111/j.1540-6261.1997.tb04813.x 1997

  4. [4]

    Cochrane, J. H. (2005). Asset Pricing (Revised ed.). Princeton University Press. https://www.johnhcochrane.com/asset-pricing

    2005

  5. [5]

    Lewellen, J., Nagel, S., & Shanken, J. (2010). A skeptical appraisal of asset-pricing tests. Journal of Financial Economics, 96(2), 175--194. https://doi.org/10.1016/j.jfineco.2009.09.001

    work page doi:10.1016/j.jfineco.2009.09.001 2010

  6. [6]

    Barillas, F., & Shanken, J. (2017). Which alpha? The Review of Financial Studies, 30(4), 1316--1338. https://doi.org/10.1093/rfs/hhw101

    work page doi:10.1093/rfs/hhw101 2017

  7. [7]

    Barillas, F., & Shanken, J. (2018). Comparing asset pricing models. The Journal of Finance, 73(2), 715--754. https://doi.org/10.1111/jofi.12607

    work page doi:10.1111/jofi.12607 2018

  8. [8]

    Kozak, S., Nagel, S., & Santosh, S. (2018). Interpreting factor models. The Journal of Finance, 73(3), 1183--1223. https://doi.org/10.1111/jofi.12612

    work page doi:10.1111/jofi.12612 2018

  9. [9]

    Y., & Zimmermann, T

    Chen, A. Y., & Zimmermann, T. (2022). Open source cross-sectional asset pricing. Critical Finance Review, 11(2), 207--264. https://doi.org/10.1561/104.00000112

    work page doi:10.1561/104.00000112 2022

  10. [10]

    Giglio, S., Xiu, D., & Zhang, D. (2025). Test assets and weak factors. The Journal of Finance, 80(1), 259--319. https://doi.org/10.1111/jofi.13415

    work page doi:10.1111/jofi.13415 2025

  11. [11]

    Shin, U. (2026). Which portfolios? The construction dependence of factor model performance. arXiv preprint arXiv:2606.19550. https://doi.org/10.48550/arXiv.2606.19550

    work page internal anchor Pith review Pith/arXiv arXiv doi:10.48550/arxiv.2606.19550 2026

  12. [12]

    Jegadeesh, N., & Titman, S. (1993). Returns to buying winners and selling losers: Implications for stock market efficiency. The Journal of Finance, 48(1), 65--91. https://doi.org/10.1111/j.1540-6261.1993.tb04702.x

    work page doi:10.1111/j.1540-6261.1993.tb04702.x 1993

  13. [13]

    Carhart, M. M. (1997). On persistence in mutual fund performance. The Journal of Finance, 52(1), 57--82. https://doi.org/10.1111/j.1540-6261.1997.tb03808.x

    work page doi:10.1111/j.1540-6261.1997.tb03808.x 1997

  14. [14]

    F., & French, K

    Fama, E. F., & French, K. R. (1992). The cross-section of expected stock returns. The Journal of Finance, 47(2), 427--465. https://doi.org/10.1111/j.1540-6261.1992.tb04398.x

    work page doi:10.1111/j.1540-6261.1992.tb04398.x 1992

  15. [15]

    F., & French, K

    Fama, E. F., & French, K. R. (1993). Common risk factors in the returns on stocks and bonds. Journal of Financial Economics, 33(1), 3--56. https://doi.org/10.1016/0304-405X(93)90023-5

    work page doi:10.1016/0304-405x(93)90023-5 1993

  16. [16]

    F., & French, K

    Fama, E. F., & French, K. R. (2015). A five-factor asset pricing model. Journal of Financial Economics, 116(1), 1--22. https://doi.org/10.1016/j.jfineco.2014.10.010

    work page doi:10.1016/j.jfineco.2014.10.010 2015

  17. [17]

    F., & French, K

    Fama, E. F., & French, K. R. (2018). Choosing factors. Journal of Financial Economics, 128(2), 234--252. https://doi.org/10.1016/j.jfineco.2018.02.012

    work page doi:10.1016/j.jfineco.2018.02.012 2018

  18. [18]

    Hou, K., Xue, C., & Zhang, L. (2015). Digesting anomalies: An investment approach. The Review of Financial Studies, 28(3), 650--705. https://doi.org/10.1093/rfs/hhu068

    work page doi:10.1093/rfs/hhu068 2015

  19. [19]

    Hou, K., Mo, H., Xue, C., & Zhang, L. (2019). Which factors? Review of Finance, 23(1), 1--35. https://doi.org/10.1093/rof/rfy032

    work page doi:10.1093/rof/rfy032 2019

  20. [20]

    Hou, K., Xue, C., & Zhang, L. (2020). Replicating anomalies. The Review of Financial Studies, 33(5), 2019--2133. https://doi.org/10.1093/rfs/hhy131

    work page doi:10.1093/rfs/hhy131 2020

  21. [21]

    Hou, K., Mo, H., Xue, C., & Zhang, L. (2021). An augmented q-factor model with expected growth. Review of Finance, 25(1), 1--41. https://doi.org/10.1093/rof/rfaa004

    work page doi:10.1093/rof/rfaa004 2021

  22. [22]

    Hou, K., Mo, H., Xue, C., & Zhang, L. (2024). The economics of security analysis. Management Science, 70(1), 164--186. https://doi.org/10.1287/mnsc.2022.4640

    work page doi:10.1287/mnsc.2022.4640 2024

  23. [23]

    Center for Research in Security Prices, LLC. (2026). CRSP US Stock Databases [Data set]. Accessed via Wharton Research Data Services, June 5, 2026. https://www.crsp.org/research/

    2026

  24. [24]

    French, K. R. (2026). Kenneth R. French Data Library [Data set]. Accessed May 5, 2026. https://mba.tuck.dartmouth.edu/pages/faculty/ken.french/data_library.html

    2026

  25. [25]

    Global-q.org. (2026). Factors and testing portfolios [Data set]. Accessed May 5, 2026. https://global-q.org/factors.html

    2026

  26. [26]

    Open Source Asset Pricing. (2026). Open Source Asset Pricing [Data set]. Accessed June 24, 2026. https://www.openassetpricing.com

    2026