pith. sign in

arxiv: 2605.18448 · v1 · pith:YA6XRXKWnew · submitted 2026-05-18 · 🧮 math.ST · econ.EM· stat.TH

Fixed-order PCA: Theory for Overestimated Factor Models

Yuan Liao , Xin Tong , Wanjie Wang , Dacheng Xiu This is my paper

Pith reviewed 2026-05-20 02:33 UTC · model grok-4.3

classification 🧮 math.ST econ.EMstat.TH
keywords factor modelsprincipal component analysisasymptotic theoryhigh-dimensional statisticsrandom matrix theoryfactor-augmented regressiontreatment effects
0
0 comments X

The pith

Principal component analysis in high-dimensional factor models remains consistent when the working dimension overestimates the true number of factors by any fixed amount.

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

The paper shows that when analysts fix the number of principal components R to be at least as large as the true number r of factors, the extra components beyond r behave like pure noise and stay nearly orthogonal to the true factor loadings. It introduces two explicit rotations—an expanded map from r to R dimensions and a compressed map from R back to r—to recover consistent factor estimates in either case. As a direct application, the same fixed-R setup delivers square-root-T asymptotic normality for factor-augmented regressions used in treatment-effect studies. A reader cares because the result justifies the everyday practice of choosing a safe upper bound on factors instead of hunting for the exact dimension.

Core claim

When the working dimension R is fixed and satisfies R greater than or equal to the true number r, the empirical eigencomponents beyond the r-th are asymptotically noise-governed, incoherent, and nearly orthogonal to the factor loadings. Two rotations, an expanded r by R map H prime and a compressed R by r map H plus, both yield consistent estimates of the latent factors. The same framework delivers square-root-T asymptotic normality for every fixed R greater than or equal to r in a factor-augmented regression for treatment-effect inference.

What carries the argument

The pair of rotations—an expanded r by R map H prime and a compressed R by r map H plus—applied to the estimated factors after the extra eigencomponents have been shown to be asymptotically noise-like.

If this is right

  • Estimated factors remain consistent under both the expanded and compressed rotations for any fixed overestimate R greater than or equal to r.
  • Extra empirical eigencomponents beyond the true r are asymptotically incoherent with the true loadings and behave like noise.
  • Square-root-T asymptotic normality holds in factor-augmented regressions for treatment-effect inference without requiring exact knowledge of r.
  • The analytical requirement reduces from consistent selection of r to the weaker task of finding any fixed upper bound on r.

Where Pith is reading between the lines

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

  • Analysts can safely default to a conservatively large but fixed R in software packages without re-running dimension-selection procedures on every new dataset.
  • The same rotation arguments may simplify inference in other high-dimensional time-series models that already use a fixed number of principal components.
  • Empirical checks could test whether the observed orthogonality between extra components and loadings holds in finite samples at the rates predicted by the local laws.

Load-bearing premise

The analysis requires that anisotropic local laws from random matrix theory continue to hold for the factor model when the working dimension R is a fixed number at least as large as the true number of factors r.

What would settle it

A simulation in which the estimated factors lose consistency or the regression coefficients lose square-root-T normality once R exceeds r by any fixed positive integer, while all other model conditions remain satisfied.

Figures

Figures reproduced from arXiv: 2605.18448 by Dacheng Xiu, Wanjie Wang, Xin Tong, Yuan Liao.

Figure 1
Figure 1. Figure 1: Empirical density of tβ across 1,000 Monte Carlo replications under the design of Experiment 1 (r = 3, α = 0, N = 200). Rows: T ∈ {100, 400, 800}. Columns: R ∈ {2, 3, 12}. Black curves are the standard-normal density. The R = 2 column (R < r) is wildly diffuse and most of its mass lies outside the plotting window. Experiment 2: varying the factor strength α [PITH_FULL_IMAGE:figures/full_fig_p020_1.png] view at source ↗
read the original abstract

We develop asymptotic theory for principal component analysis (PCA) of a high-dimensional factor model in which the working dimension $R$ is fixed and only required to satisfy $R \ge r$, where $r$ is the true number of factors. Building on anisotropic local laws from random matrix theory, we show that the ``extra'' empirical eigencomponents beyond the $r$-th are asymptotically noise-governed, incoherent, and nearly orthogonal to the factor loadings. We introduce two rotations, an expanded $r\times R$ map $H'$ and a compressed $R\times r$ map $H^{+}$, and establish consistency of the estimated factors under both. As an application, we analyze a factor-augmented regression for treatment-effect inference and prove $\sqrt{T}$-asymptotic normality for every fixed $R \ge r$. These results provide a theoretical underpinning for the common empirical practice of adopting a conservative upper bound on the number of factors, and shift the analytical burden from consistent dimension selection to the milder requirement of bounding $r$ from above.

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

2 major / 2 minor

Summary. The manuscript develops asymptotic theory for principal component analysis (PCA) of high-dimensional factor models where the working dimension R is fixed and satisfies only R ≥ r (r the true number of factors). Building on anisotropic local laws from random matrix theory, it shows that the extra empirical eigencomponents beyond the r-th are asymptotically noise-governed, incoherent, and nearly orthogonal to the factor loadings. Two rotations—an expanded r×R map H' and a compressed R×r map H+—are introduced, consistency of the estimated factors is established under both, and √T-asymptotic normality is proved for every fixed R ≥ r in a factor-augmented regression for treatment-effect inference.

Significance. If the central claims hold, the results supply a rigorous justification for the widespread empirical practice of adopting a conservative upper bound on the number of factors rather than insisting on consistent dimension selection. The consistency statements under the two rotations and the √T-normality result in the regression application are concrete contributions that could be used in econometric and statistical work with factor-augmented models. The explicit use of anisotropic local laws is a technical strength when the model-specific conditions are verified.

major comments (2)
  1. [Abstract and main derivation (likely §3–4)] Abstract and the derivation of the main results on extra eigencomponents: the claims that these components are asymptotically noise-governed, incoherent, and nearly orthogonal to the factor loadings rest on anisotropic local laws holding uniformly for the fixed number of extra directions when R > r. The manuscript invokes these laws for the sample covariance of the model ΛF + E but does not appear to contain an explicit verification that the row-wise dependence structure or moment conditions on the idiosyncratic matrix E satisfy the hypotheses of the cited local-law theorems (which are typically stated for i.i.d. or Wigner-type ensembles). This verification is load-bearing for the subsequent incoherence and near-orthogonality statements used to justify the rotations H' and H+.
  2. [Section introducing H' and H+ and the consistency theorems] Consistency of estimated factors under H' and H+ (the two rotations introduced after the local-law step): the argument that the extra components remain nearly orthogonal relies on the uniformity of the local laws for the fixed extra directions orthogonal to the column space of Λ. If this uniformity is not established, the claimed consistency rates may not follow at the stated order; a concrete counter-example or additional bound under the paper’s moment assumptions on E would strengthen the result.
minor comments (2)
  1. The notation for the two rotations H' (r×R) and H+ (R×r) is introduced without an immediate diagram or explicit matrix expression; adding a short display equation or schematic early in the paper would improve readability.
  2. Ensure that every invocation of an anisotropic local law includes the precise theorem number and the exact set of assumptions from the reference that are being used.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the careful and constructive report. The comments correctly identify the need for explicit verification of the local-law hypotheses and for a clearer uniformity argument in the consistency proofs. We address both points below and will revise the manuscript to incorporate the requested clarifications and additional bounds.

read point-by-point responses

  1. Referee: [Abstract and main derivation (likely §3–4)] Abstract and the derivation of the main results on extra eigencomponents: the claims that these components are asymptotically noise-governed, incoherent, and nearly orthogonal to the factor loadings rest on anisotropic local laws holding uniformly for the fixed number of extra directions when R > r. The manuscript invokes these laws for the sample covariance of the model ΛF + E but does not appear to contain an explicit verification that the row-wise dependence structure or moment conditions on the idiosyncratic matrix E satisfy the hypotheses of the cited local-law theorems (which are typically stated for i.i.d. or Wigner-type ensembles). This verification is load-bearing for the subsequent incoherence and near-orthogonality statements used to justify the rotations H' and H+.

    Authors: We agree that an explicit verification is required for rigor. In the revised manuscript we will insert a dedicated subsection (new §3.2) that checks the moment and dependence conditions on E against the hypotheses of the cited anisotropic local-law theorems. Under our maintained assumptions—sub-exponential tails on the entries of E together with weak cross-sectional dependence that is uniform in the fixed dimension R—the row-wise covariance structure satisfies the required bounds, and the low-rank perturbation ΛF is absorbed into the spiked-model framework. This verification will be stated uniformly over the fixed number of extra directions, directly supporting the incoherence and near-orthogonality claims that justify the rotations H' and H+. revision: yes

  2. Referee: [Section introducing H' and H+ and the consistency theorems] Consistency of estimated factors under H' and H+ (the two rotations introduced after the local-law step): the argument that the extra components remain nearly orthogonal relies on the uniformity of the local laws for the fixed extra directions orthogonal to the column space of Λ. If this uniformity is not established, the claimed consistency rates may not follow at the stated order; a concrete counter-example or additional bound under the paper’s moment assumptions on E would strengthen the result.

    Authors: We concur that uniformity over the fixed extra directions must be made explicit. Because R is fixed, the number of extra directions is bounded independently of T and N; the local laws therefore apply uniformly by a standard finite-union argument once the moment conditions on E are verified. In the revision we will add a short lemma (new Lemma 4.3) that supplies an explicit high-probability bound on the inner products between the extra empirical eigenvectors and the column space of Λ, using only the paper’s existing moment assumptions on E. With this bound in hand the consistency rates for the rotated factor estimates under both H' and H+ follow at the stated order. We do not provide a counter-example, as the strengthened bound will confirm the claimed rates rather than refute them. revision: yes

Circularity Check

0 steps flagged

No significant circularity; central results built on external random matrix theory

full rationale

The paper derives its main results on extra eigencomponents being noise-governed and factor consistency by invoking anisotropic local laws from random matrix theory as an external foundation, rather than defining them internally or fitting parameters that are then renamed as predictions. No load-bearing step reduces by construction to self-citations or ansatzes within the paper; the analysis treats the local laws as given under the fixed-R regime and focuses on their implications for rotations H' and H+ and subsequent normality. This is a standard use of prior RMT results and keeps the derivation self-contained against external benchmarks.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on external random matrix theory results and the structural assumption of a high-dimensional factor model with fixed working dimension R ≥ r; no free parameters or new entities are introduced in the abstract.

axioms (1)
  • domain assumption Anisotropic local laws from random matrix theory apply to the high-dimensional factor model with fixed R ≥ r
    Invoked to establish that extra eigencomponents are noise-governed and to prove consistency and normality.

pith-pipeline@v0.9.0 · 5716 in / 1334 out tokens · 49677 ms · 2026-05-20T02:33:22.511115+00:00 · methodology

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

300 extracted references · 300 canonical work pages · 7 internal anchors

  1. [1]

    Biometrika , pages=

    Network-adjusted covariates for community detection , author=. Biometrika , pages=. 2024 , publisher=

    work page 2024

  2. [2]

    Econometrica , volume=

    Confidence intervals for diffusion index forecasts and inference for factor-augmented regressions , author=. Econometrica , volume=. 2006 , publisher=

    work page 2006

  3. [3]

    Probability Theory and Related Fields , volume=

    Anisotropic local laws for random matrices , author=. Probability Theory and Related Fields , volume=. 2017 , publisher=

    work page 2017

  4. [4]

    Annual Review of Financial Economics , volume=

    Recent developments in factor models and applications in econometric learning , author=. Annual Review of Financial Economics , volume=. 2021 , publisher=

    work page 2021

  5. [5]

    Journal of monetary Economics , volume=

    The equity premium: A puzzle , author=. Journal of monetary Economics , volume=. 1985 , publisher=

    work page 1985

  6. [6]

    Available at SSRN 3512123 , year=

    Macroeconomic Content of Characteristics-Based Asset Pricing Models: A Machine Learning Analysis , author=. Available at SSRN 3512123 , year=

    work page

  7. [7]

    Annals of Applied Probability , year=

    Universality of covariance matrices , author=. Annals of Applied Probability , year=

    work page

  8. [8]

    2015 , journal=

    Delocalization of eigenvectors of random matrices with independent entries , author=. 2015 , journal=

    work page 2015

  9. [9]

    2018 , publisher=

    High-dimensional probability: An introduction with applications in data science , author=. 2018 , publisher=

    work page 2018

  10. [10]

    Electronic Journal of Probability , author=

    Isotropic local laws for sample covariance and generalized. Electronic Journal of Probability , author=

    work page

  11. [11]

    The Journal of Finance , volume=

    On the predictability of stock returns: an asset-allocation perspective , author=. The Journal of Finance , volume=. 1996 , publisher=

    work page 1996

  12. [12]

    Goldman Sachs Fixed Income Research , volume=

    Asset allocation: combining investor views with market equilibrium , author=. Goldman Sachs Fixed Income Research , volume=

    work page

  13. [13]

    Mathematics of control, signals and systems , volume=

    Approximation by superpositions of a sigmoidal function , author=. Mathematics of control, signals and systems , volume=. 1989 , publisher=

    work page 1989

  14. [14]

    Neural networks , volume=

    Multilayer feedforward networks are universal approximators , author=. Neural networks , volume=. 1989 , publisher=

    work page 1989

  15. [15]

    Advances in neural information processing systems , volume=

    Random features for large-scale kernel machines , author=. Advances in neural information processing systems , volume=

    work page

  16. [16]

    The Review of Financial Studies , volume=

    Predicting excess stock returns out of sample: Can anything beat the historical average? , author=. The Review of Financial Studies , volume=. 2008 , publisher=

    work page 2008

  17. [17]

    Adam: A Method for Stochastic Optimization

    Adam: A method for stochastic optimization , author=. arXiv preprint arXiv:1412.6980 , year=

    work page internal anchor Pith review Pith/arXiv arXiv

  18. [18]

    Journal of the Royal statistical society: series B (Methodological) , volume=

    Controlling the false discovery rate: a practical and powerful approach to multiple testing , author=. Journal of the Royal statistical society: series B (Methodological) , volume=. 1995 , publisher=

    work page 1995

  19. [19]

    Financial Analysts Journal , volume=

    Do sales--price and debt--equity explain stock returns better than book--market and firm size? , author=. Financial Analysts Journal , volume=. 1996 , publisher=

    work page 1996

  20. [20]

    The Journal of Finance , volume=

    Price, beta, and exchange listing , author=. The Journal of Finance , volume=. 1973 , publisher=

    work page 1973

  21. [21]

    Journal of financial economics , volume=

    Market underreaction to open market share repurchases , author=. Journal of financial economics , volume=. 1995 , publisher=

    work page 1995

  22. [22]

    Journal of Financial Economics , Year =

    Commonality in determinants of expected stock returns , Author =. Journal of Financial Economics , Year =

    work page

  23. [23]

    Journal of Financial Economics , Year =

    The relationship between return and market value of common stocks , Author =. Journal of Financial Economics , Year =

    work page

  24. [24]

    Journal of Finance , volume=

    Market reactions to tangible and intangible information , author=. Journal of Finance , volume=. 2006 , publisher=

    work page 2006

  25. [25]

    Journal of Finance , year =

    Pontiff, Jeffrey and Woodgate, Artemiza , title =. Journal of Finance , year =

    work page

  26. [26]

    2016 , publisher=

    Empirical asset pricing: The cross section of stock returns , author=. 2016 , publisher=

    work page 2016

  27. [27]

    Journal of Empirical Finance , volume=

    Residual momentum , author=. Journal of Empirical Finance , volume=. 2011 , publisher=

    work page 2011

  28. [28]

    The Review of Financial Studies , volume=

    Market frictions, price delay, and the cross-section of expected returns , author=. The Review of Financial Studies , volume=. 2005 , publisher=

    work page 2005

  29. [29]

    Bali and Nusret Cakici and Robert F

    Turan G. Bali and Nusret Cakici and Robert F. Whitelaw , title =. Journal of Financial Economics , year =. doi:https://doi.org/10.1016/j.jfineco.2010.08.014 , keywords =

    work page doi:10.1016/j.jfineco.2010.08.014 2010

  30. [30]

    Journal of Accounting and Economics , volume=

    The relation between corporate financing activities, analysts’ forecasts and stock returns , author=. Journal of Accounting and Economics , volume=. 2006 , publisher=

    work page 2006

  31. [31]

    Journal of Finance , Year =

    Debt/equity ratio and expected common stock returns: Empirical evidence , Author =. Journal of Finance , Year =

    work page

  32. [32]

    Journal of Finance , Year =

    Does the stock market overreact? , Author =. Journal of Finance , Year =

    work page

  33. [33]

    Journal of Financial and Quantitative Analysis , volume=

    Capital investments and stock returns , author=. Journal of Financial and Quantitative Analysis , volume=. 2004 , publisher=

    work page 2004

  34. [34]

    Journal of Financial Economics , volume=

    Seasonality in the cross-section of stock returns , author=. Journal of Financial Economics , volume=. 2008 , publisher=

    work page 2008

  35. [35]

    Journal of Financial Economics , volume=

    Alternative factor specifications, security characteristics, and the cross-section of expected stock returns , author=. Journal of Financial Economics , volume=. 1998 , publisher=

    work page 1998

  36. [36]

    Review of Financial Studies , Year =

    The new issues puzzle: Testing the investment-based explanation , Author =. Review of Financial Studies , Year =

    work page

  37. [37]

    Labor Hiring, Investment, and Stock Return Predictability in the Cross Section , volume =

    Frederico Belo and Xiaoji Lin and Santiago Bazdresch , journal =. Labor Hiring, Investment, and Stock Return Predictability in the Cross Section , volume =

    work page

  38. [38]

    Journal of Finance , volume=

    Empirical evidence on capital investment, growth options, and security returns , author=. Journal of Finance , volume=. 2006 , publisher=

    work page 2006

  39. [39]

    Accounting Review , pages=

    Earnings releases, anomalies, and the behavior of security returns , author=. Accounting Review , pages=. 1984 , publisher=

    work page 1984

  40. [40]

    Review of Accounting Studies , volume=

    Implied equity duration: A new measure of equity risk , author=. Review of Accounting Studies , volume=. 2004 , publisher=

    work page 2004

  41. [41]

    Review of Financial Studies , volume=

    The inventory growth spread , author=. Review of Financial Studies , volume=. 2012 , publisher=

    work page 2012

  42. [42]

    Journal of Financial Economics , volume=

    Profitability, investment and average returns , author=. Journal of Financial Economics , volume=. 2006 , publisher=

    work page 2006

  43. [43]

    Accounting Review , volume=

    Do investors understand really dirty surplus? , author=. Accounting Review , volume=

    work page

  44. [44]

    Accounting Review , volume=

    Taxable income, future earnings, and equity values , author=. Accounting Review , volume=

    work page

  45. [45]

    Accounting Review , volume=

    Value-glamour and accruals mispricing: One anomaly or two? , author=. Accounting Review , volume=

    work page

  46. [46]

    Journal of Financial Economics , volume=

    Arbitrage risk and the book-to-market anomaly , author=. Journal of Financial Economics , volume=. 2003 , publisher=

    work page 2003

  47. [47]

    Journal of Finance , Year =

    The cross-section of volatility and expected returns , Author =. Journal of Finance , Year =

    work page

  48. [48]

    Journal of Finance , year =

    Basu, Sanjoy , title =. Journal of Finance , year =

    work page

  49. [49]

    Accounting Review , pages=

    Abnormal returns to a fundamental analysis strategy , author=. Accounting Review , pages=. 1998 , publisher=

    work page 1998

  50. [50]

    Unpublished Manuscript, UT Austin , year =

    Chandrashekar, Satyajit and Rao, Ramesh KS , title =. Unpublished Manuscript, UT Austin , year =

    work page

  51. [51]

    Journal of Financial Economics , volume=

    Asset pricing and the bid-ask spread , author=. Journal of Financial Economics , volume=. 1986 , publisher=

    work page 1986

  52. [52]

    Journal of Finance , Year =

    Asset growth and the cross-section of stock returns , Author =. Journal of Finance , Year =

    work page

  53. [53]

    Journal of Financial Economics , Year =

    Is momentum really momentum? , Author =. Journal of Financial Economics , Year =

    work page

  54. [54]

    Review of Finance , Year =

    Operating leverage , Author =. Review of Finance , Year =

    work page

  55. [55]

    Journal of Financial Economics , Year =

    Cash holdings, risk, and expected returns , Author =. Journal of Financial Economics , Year =

    work page

  56. [56]

    Journal of Finance , Year =

    Evidence of predictable behavior of security returns , Author =. Journal of Finance , Year =

    work page

  57. [57]

    Journal of Financial Research , volume=

    Sustainable growth and stock returns , author=. Journal of Financial Research , volume=. 2010 , publisher=

    work page 2010

  58. [58]

    Journal of Finance , volume=

    Conditional Skewness in Asset Pricing Tests , author=. Journal of Finance , volume=. 2000 , publisher=

    work page 2000

  59. [59]

    and Womack, Kent L

    Michaely, Roni and Thaler, Richard H. and Womack, Kent L. , title =. Journal of Finance , volume =

    work page

  60. [60]

    Journal of Financial and Quantitative Analysis , volume=

    New Evidence on the Relation between the Enterprise Multiple and Average Stock Returns , author=. Journal of Financial and Quantitative Analysis , volume=. 2011 , publisher=

    work page 2011

  61. [61]

    and Ikenberry, David L

    Dharan, Bala G. and Ikenberry, David L. , title =. Journal of Finance , volume =

    work page

  62. [62]

    Journal of Financial Economics , volume=

    Differential information and the small firm effect , author=. Journal of Financial Economics , volume=. 1984 , publisher=

    work page 1984

  63. [63]

    Accounting Review , volume=

    Accrued Earnings and Growth: Implications for Future Profitability and Market Mispricing , author=. Accounting Review , volume=

    work page

  64. [64]

    Journal of Finance , volume=

    Industry Concentration and Average Stock Returns , author=. Journal of Finance , volume=. 2006 , publisher=

    work page 2006

  65. [65]

    Journal of Financial Markets , volume=

    Illiquidity and stock returns: cross-section and time-series effects , author=. Journal of Financial Markets , volume=. 2002 , publisher=

    work page 2002

  66. [66]

    Journal of Finance , volume=

    Do Industries Explain Momentum? , author=. Journal of Finance , volume=. 1999 , publisher=

    work page 1999

  67. [67]

    Journal of Financial Economics , volume=

    A liquidity-augmented capital asset pricing model , author=. Journal of Financial Economics , volume=. 2006 , publisher=

    work page 2006

  68. [68]

    Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , year =

    Jegadeesh, Narasimhan and Titman, Sheridan , journal =. Returns to Buying Winners and Selling Losers: Implications for Stock Market Efficiency , year =

    work page

  69. [69]

    Review of Financial Studies , volume =

    Tail risk and asset prices , author =. Review of Financial Studies , volume =. 2014 , publisher =

    work page 2014

  70. [70]

    Journal of Accounting and Economics , year =

    Ou, Jane A and Penman, Stephen H , title =. Journal of Accounting and Economics , year =

    work page

  71. [71]

    Unpublished Manuscript, AQR , year =

    Asness, Clifford S and Porter, R Burt and Stevens, Ross L , title =. Unpublished Manuscript, AQR , year =

    work page

  72. [72]

    Journal of Finance , year =

    Lakonishok, Josef and Shleifer, Andrei and Vishny, Robert W , title =. Journal of Finance , year =

    work page

  73. [73]

    Journal of Financial Economics , year =

    Chordia, Tarun and Subrahmanyam, Avanidhar and Anshuman, V Ravi , title =. Journal of Financial Economics , year =

    work page

  74. [74]

    Review of Accounting Studies , year =

    Thomas, Jacob K and Zhang, Huai , title =. Review of Accounting Studies , year =

    work page

  75. [75]

    Accounting Review , Year =

    Do stock prices fully reflect information in accruals and cash flows about future earnings? , Author =. Accounting Review , Year =

    work page

  76. [76]

    Journal of Financial Economics , Year =

    Betting against beta , Author =. Journal of Financial Economics , Year =

    work page

  77. [77]

    Journal of Accounting and Economics , year =

    Richardson, Scott A and Sloan, Richard G and Soliman, Mark T and Tuna, Irem , title =. Journal of Accounting and Economics , year =

    work page

  78. [78]

    The accounting review , author =

    The use of. The accounting review , author =. 2008 , pages =

    work page 2008

  79. [79]

    Journal of Financial and Quantitative Analysis , author =

    Strategic default, debt structure, and stock returns , volume =. Journal of Financial and Quantitative Analysis , author =. 2016 , note =

    work page 2016

  80. [80]

    Journal of Financial Economics , author =

    The dividend month premium , volume =. Journal of Financial Economics , author =. 2013 , note =

    work page 2013

Showing first 80 references.