pith. sign in

arxiv: 2606.27654 · v1 · pith:PWUL3IDXnew · submitted 2026-06-26 · 📊 stat.ME

Modeling Educational Performance Using School Demographics and Teacher Characteristics

Brianna Reed , Paramahansa Pramanik This is my paper

Pith reviewed 2026-06-29 03:53 UTC · model grok-4.3

classification 📊 stat.ME
keywords Adaptive Weighted Group Fused LASSOpenalized regressionvariable selectiongroup regularizationcoefficient fusioneducational data analysishigh-dimensional statisticsADMM algorithm
0
0 comments X

The pith

The Adaptive Weighted Group Fused LASSO estimator performs variable selection, group regularization, and coefficient fusion for high-dimensional educational data.

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

The paper introduces a new penalized regression method tailored for educational datasets that are high-dimensional with sparse, grouped, and locally correlated predictors. It unifies adaptive selection, group penalties, and fusion of coefficients in one framework, backed by an ADMM solver and proofs of consistency and oracle properties. Simulations show better performance than standard methods, and the approach is applied to Alabama school math data to find key predictors of proficiency. A reader would care if these data features are common in education research, as better models could lead to more reliable identification of what drives student outcomes.

Core claim

The authors propose an Adaptive Weighted Group Fused LASSO estimator that jointly performs adaptive variable selection, group regularization, and coefficient fusion within a unified penalized regression framework, develop an efficient ADMM algorithm, and establish asymptotic properties including consistency, oracle property, and debiased asymptotic normality, with superior performance shown in simulations and an application to Alabama public school mathematics proficiency data.

What carries the argument

The Adaptive Weighted Group Fused LASSO estimator, which unifies adaptive variable selection, group regularization, and coefficient fusion in a single penalized regression setup.

If this is right

  • Simulation studies show superior estimation and prediction performance over existing penalized regression methods.
  • The method improves model interpretability and predictive accuracy when modeling Alabama public school mathematics proficiency.
  • It identifies the most influential institutional predictors in the educational dataset.
  • Theoretical guarantees include consistency, oracle property, and debiased asymptotic normality for reliable inference.

Where Pith is reading between the lines

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

  • Similar data structures appear in other high-dimensional domains like genomics, suggesting the estimator could extend beyond education.
  • The fusion of coefficients may help capture similar effects among related demographic or teacher variables.
  • Testing the method on datasets from other states or subjects could validate its broader utility in education policy analysis.

Load-bearing premise

High-dimensional educational datasets exhibit sparsity, grouped predictors, and locally correlated covariates that make conventional regression methods ineffective.

What would settle it

Empirical results on a high-dimensional educational dataset where standard LASSO or group LASSO achieves comparable or better estimation accuracy, prediction error, and interpretability than the proposed estimator.

Figures

Figures reproduced from arXiv: 2606.27654 by Brianna Reed, Paramahansa Pramanik.

Figure 1
Figure 1. Figure 1: Overall simulation performance of the competing penalized regression estimators. Each bar sum [PITH_FULL_IMAGE:figures/full_fig_p046_1.png] view at source ↗
Figure 2
Figure 2. Figure 2: Proficiency Rate Distribution [PITH_FULL_IMAGE:figures/full_fig_p048_2.png] view at source ↗
Figure 3
Figure 3. Figure 3: Summary of Measure Means 52 [PITH_FULL_IMAGE:figures/full_fig_p052_3.png] view at source ↗
Figure 5
Figure 5. Figure 5: Mean Proficiency Rate by Race and SES White Minority White ED Minority ED 0 5 10 15 20 25 Predominant Demographic in School’s Population % of Teachers with These Certifications [PITH_FULL_IMAGE:figures/full_fig_p053_5.png] view at source ↗
Figure 6
Figure 6. Figure 6: Mean Emergency or Provisional Certification Rate by Race and SES [PITH_FULL_IMAGE:figures/full_fig_p053_6.png] view at source ↗
read the original abstract

High-dimensional educational datasets often exhibit sparsity, grouped predictors, and locally correlated covariates, limiting the effectiveness of conventional regression methods. We propose an Adaptive Weighted Group Fused LASSO estimator that jointly performs adaptive variable selection, group regularization, and coefficient fusion within a unified penalized regression framework. An efficient ADMM algorithm is developed, and asymptotic properties, including consistency, oracle property, and debiased asymptotic normality, are established. Simulation studies demonstrate superior estimation and prediction performance compared with existing penalized methods. An application to Alabama public school mathematics proficiency data illustrates improved model interpretability, predictive accuracy, and identification of the most influential institutional predictors.

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 / 0 minor

Summary. The paper claims to introduce an Adaptive Weighted Group Fused LASSO estimator for high-dimensional educational data that combines adaptive variable selection, group regularization, and coefficient fusion. It develops an ADMM algorithm and establishes asymptotic properties such as consistency, oracle property, and debiased asymptotic normality. Simulation studies show superior performance, and an application to Alabama school data shows improved interpretability and accuracy.

Significance. If the theoretical results are rigorously derived and the empirical claims hold, this could be a useful addition to penalized regression methods for structured high-dimensional data in education. The unified framework and algorithm are strengths. However, the significance is limited by the unverified assumption about the data structures in educational datasets.

major comments (2)
  1. [Abstract] Abstract: The assertion of asymptotic properties including the oracle property is made without providing derivation steps, explicit conditions, or quantitative simulation results, leaving the central claims unsupported at the level required for evaluation.
  2. [Application] Application: The Alabama application is described only as showing improved interpretability and accuracy; no evidence is referenced that the predictors display the required sparsity pattern, natural grouping, or local correlation structure that would make the fusion beneficial, which is load-bearing for the motivation of the new estimator.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for their constructive comments. We respond point-by-point to the major comments below.

read point-by-point responses

  1. Referee: [Abstract] Abstract: The assertion of asymptotic properties including the oracle property is made without providing derivation steps, explicit conditions, or quantitative simulation results, leaving the central claims unsupported at the level required for evaluation.

    Authors: Abstracts are designed to summarize contributions at a high level; detailed derivations, conditions, and proofs are not appropriate there. The asymptotic results (consistency, oracle property, and debiased asymptotic normality) with explicit conditions are derived in Section 3, with full proofs in the Appendix. Quantitative simulation results appear in Section 5. The claims are therefore supported by the manuscript as a whole, and we see no need to alter the abstract. revision: no

  2. Referee: [Application] Application: The Alabama application is described only as showing improved interpretability and accuracy; no evidence is referenced that the predictors display the required sparsity pattern, natural grouping, or local correlation structure that would make the fusion beneficial, which is load-bearing for the motivation of the new estimator.

    Authors: We agree that explicit verification of the data structures would strengthen the motivation. In the revised manuscript we will add supporting analyses, including pairwise correlation matrices and assessments of sparsity and grouping among the school-level predictors, to demonstrate that the Alabama data exhibit the local correlation and grouped structure assumed by the estimator. revision: yes

Circularity Check

0 steps flagged

No circularity: new estimator, algorithm, and asymptotics derived independently of data fits or self-citations

full rationale

The paper proposes the Adaptive Weighted Group Fused LASSO as a new unified penalized framework, develops a separate ADMM algorithm, and derives consistency, oracle property, and debiased normality via standard asymptotic arguments. These steps are presented as mathematical constructions rather than reductions of fitted parameters or data-defined quantities. No self-citations appear in the provided text to justify uniqueness or ansatzes, and simulation/application results are offered as external validation rather than the source of the claimed properties. The opening premise about data structures is an empirical motivation, not a load-bearing step that collapses the derivation by construction.

Axiom & Free-Parameter Ledger

0 free parameters · 0 axioms · 0 invented entities

Abstract-only review yields no explicit free parameters, axioms, or invented entities; the method implicitly assumes standard regularity conditions for penalized regression asymptotics, but none are stated.

pith-pipeline@v0.9.1-grok · 5623 in / 1166 out tokens · 42721 ms · 2026-06-29T03:53:32.274438+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

252 extracted references · 27 canonical work pages · 2 internal anchors

  1. [1]

    , title =

    Flores, A. , title =. The High School Journal , volume =

  2. [3]

    , title =

    Reis, Miguel and Brites, Nuno M. , title =. Results in Applied Mathematics , volume =. 2025 , doi =

    2025

  3. [4]

    and Braumann, Carlos A

    Brites, Nuno M. and Braumann, Carlos A. , title =. Stochastic Models , volume =. 2023 , doi =

    2023

  4. [5]

    , title =

    Brites, Nuno M. , title =. Mathematics , volume =. 2022 , doi =

    2022

  5. [6]

    and Ryan, Dennis , title =

    Hanson, Floyd B. and Ryan, Dennis , title =. Mathematical Biosciences , volume =. 1998 , doi =

    1998

  6. [7]

    Optimal Harvesting from Interacting Populations in a Stochastic Environment , journal =

    Lungu, Edward and. Optimal Harvesting from Interacting Populations in a Stochastic Environment , journal =. 2001 , doi =

    2001

  7. [8]

    Journal of Mathematical Biology , volume =

    Hening, Alexandru and Tran, Ky Quan , title =. Journal of Mathematical Biology , volume =. 2020 , doi =

    2020

  8. [9]

    Bellman, Richard , title =

  9. [10]

    and Soner, Halil Mete , title =

    Fleming, Wendell H. and Soner, Halil Mete , title =

  10. [11]

    , title =

    Feynman, Richard P. , title =. Reviews of Modern Physics , volume =. 1948 , doi =

    1948

  11. [12]

    Transactions of the American Mathematical Society , volume =

    Kac, Mark , title =. Transactions of the American Mathematical Society , volume =. 1949 , doi =

    1949

  12. [13]

    Adapted Solution of a Backward Stochastic Differential Equation , journal =

    Pardoux,. Adapted Solution of a Backward Stochastic Differential Equation , journal =. 1990 , doi =

    1990

  13. [14]

    Capture Fisheries Production (Metric Tons), Indicator ER.FSH.CAPT.MT , year =

  14. [15]

    Global Capture Production Database , year =

  15. [16]

    Statistics & Probability Letters , volume=

    Assessing bivariate tail non-exchangeable dependence , author=. Statistics & Probability Letters , volume=. 2019 , publisher=

    2019

  16. [17]

    Analytics , volume=

    Playmydata: A statistical analysis of a video game dataset on review scores and gaming platforms , author=. Analytics , volume=. 2025 , publisher=

    2025

  17. [19]

    European Journal of Statistics , volume=

    The Role of MYB in Prostate Cancer: A Statistical Analysis , author=. European Journal of Statistics , volume=

  18. [20]

    arXiv preprint arXiv:2601.10615 , year=

    A Bayesian Discrete Framework for Enhancing Decision-Making Processes in Clinical Trial Designs and Evaluations , author=. arXiv preprint arXiv:2601.10615 , year=

    work page arXiv

  19. [23]

    International Conference on Mathematical Modeling in Physical Sciences , pages=

    Analysis of a Tiered Pricing Model for eCW Clients , author=. International Conference on Mathematical Modeling in Physical Sciences , pages=. 2024 , organization=

    2024

  20. [24]

    The FASEB Journal , volume=

    Frequent Loss of CACNA1C Is Associated With Poor Prognosis in Non-Small Cell Lung Cancer , author=. The FASEB Journal , volume=. 2026 , publisher=

    2026

  21. [25]

    International Game Theory Review , pages=

    Strategic Dynamics of Firms via Path Integral Control , author=. International Game Theory Review , pages=. 2026 , publisher=

    2026

  22. [26]

    bioRxiv , pages=

    Angiotensin II Type 1 Receptor Blockade Inhibits Gastric Cancer Metastasis Through Tight Junction Restoration , author=. bioRxiv , pages=. 2026 , publisher=

    2026

  23. [27]

    Journal of Urology , volume=

    Mp60-05 myb exhibits racially disparate expression and clinicopathologic association and is a promising predictor of biochemical recurrence in prostate cancer , author=. Journal of Urology , volume=. 2024 , publisher=

    2024

  24. [28]

    Cancer Research , volume=

    Frequent loss of CACNA1C, a calcium voltage-gated channel subunit is associated with lung adenocarcinoma progression and poor prognosis , author=. Cancer Research , volume=. 2023 , publisher=

    2023

  25. [29]

    International Journal of Molecular Sciences , volume=

    Cardiovascular Complications in Patients with Prostate Cancer: Potential Molecular Connections , author=. International Journal of Molecular Sciences , volume=. 2023 , publisher=

    2023

  26. [30]

    PeerJ , volume=

    New approaches for capturing and estimating variation in complex animal color patterns from digital photographs: application to the Eastern Box Turtle (Terrapene carolina) , author=. PeerJ , volume=. 2025 , publisher=

    2025

  27. [31]

    BMC Research Notes , volume=

    Assessing CometChip technology for DNA damage studies in non-model species: distinct UV-induced responses in turtles and mammals , author=. BMC Research Notes , volume=. 2025 , publisher=

    2025

  28. [32]

    26 (2023) 108487 ,

    Myb exhibits racially disparate expression, clinicopathologic association, and predictive potential for biochemical recurrence in prostate cancer, iScience. 26 (2023) 108487 ,

    2023

  29. [33]

    European Journal of Statistics , volume=

    Association between Obesity, Race, and Luminal Subtypes of Breast Cancer , author=. European Journal of Statistics , volume=

  30. [36]

    Mathematics , volume=

    Construction of an Optimal Strategy: An Analytic Insight Through Path Integral Control Driven by a McKean--Vlasov Opinion Dynamics , author=. Mathematics , volume=. 2025 , publisher=

    2025

  31. [38]

    Onco , volume=

    Prognostic Role of B7-H3 (CD276) Expression in Initial Biopsies of Metastatic Prostate Cancer , author=. Onco , volume=. 2025 , publisher=

    2025

  32. [40]

    European Journal of Statistics , volume=

    Strategic Complementarities Due to Monetary Shock Under Sticky Price , author=. European Journal of Statistics , volume=

  33. [43]

    European Journal of Statistics , volume=

    Strategies to Increase Pipeline Status: A Case Study from Eclinical Data , author=. European Journal of Statistics , volume=

  34. [45]

    Mathematics , volume=

    Stubbornness as Control in Professional Soccer Games: A BPPSDE Approach , author=. Mathematics , volume=. 2025 , publisher=

    2025

  35. [46]

    SN Operations Research Forum , volume=

    Optimization of market stochastic dynamics , author=. SN Operations Research Forum , volume=. 2020 , publisher=

    2020

  36. [47]

    Stochastic Control in Determining a Soccer Player’s Performance , author=. J. Compr. Pure Appl. Math , volume=

  37. [48]

    European Journal of Statistics , volume=

    Measuring Asymmetric Tails Under Copula Distributions , author=. European Journal of Statistics , volume=

  38. [49]

    J , volume=

    Dependence on Tail Copula , author=. J , volume=. 2024 , publisher=

    2024

  39. [50]

    On Estimation of Function-on-function Regression Kernels with Brownian Berkson Errors , author=

  40. [51]

    European Journal of Statistics , volume=

    Estimation of optimal lock-down and vaccination rate of a stochastic sir model: A mathematical approach , author=. European Journal of Statistics , volume=

  41. [54]

    Cancer Research , volume=

    Abstract PO3-16-05: Mitochondrial DNA mutation detection in tumors and circulating extracellular vesicles of triple negative breast cancer patients for biomarker development , author=. Cancer Research , volume=. 2024 , publisher=

    2024

  42. [55]

    CANCER RESEARCH , volume=

    Mitochondrial DNA mutation detection in tumors and circulating extracellular vesicles of triple negative breast cancer patients for biomarker development , author=. CANCER RESEARCH , volume=. 2024 , organization=

    2024

  43. [56]

    The FASEB Journal , volume=

    Clinicopathological significance of unraveling mitochondrial pathway alterations in non-small-cell lung cancer , author=. The FASEB Journal , volume=. 2023 , publisher=

    2023

  44. [57]

    FASEB BioAdvances , volume=

    Profiling mitochondrial DNA mutations in tumors and circulating extracellular vesicles of triple-negative breast cancer patients for potential biomarker development , author=. FASEB BioAdvances , volume=. 2023 , publisher=

    2023

  45. [58]

    Iscience , volume=

    MYB exhibits racially disparate expression, clinicopathologic association, and predictive potential for biochemical recurrence in prostate cancer , author=. Iscience , volume=. 2023 , publisher=

    2023

  46. [59]

    Stats , volume=

    Parametric Estimation in Fractional Stochastic Differential Equation , author=. Stats , volume=. 2024 , publisher=

    2024

  47. [60]

    Computational and Mathematical Biophysics , volume=

    Optimal lock-down intensity: A stochastic pandemic control approach of path integral , author=. Computational and Mathematical Biophysics , volume=. 2023 , publisher=

    2023

  48. [61]

    Mathematics , volume=

    Motivation to Run in One-Day Cricket , author=. Mathematics , volume=. 2024 , publisher=

    2024

  49. [62]

    2021 , school=

    Optimization of Dynamic Objective Functions Using Path Integrals , author=. 2021 , school=

    2021

  50. [63]

    Computational Statistics & Data Analysis , volume=

    A motif building process for simulating random networks , author=. Computational Statistics & Data Analysis , volume=. 2021 , publisher=

    2021

  51. [65]

    Theory in Biosciences , pages=

    Path integral control of a stochastic multi-risk SIR pandemic model , author=. Theory in Biosciences , pages=. 2023 , publisher=

    2023

  52. [66]

    The Journal of Mathematical Sociology , pages=

    Semicooperation under curved strategy spacetime , author=. The Journal of Mathematical Sociology , pages=. 2023 , publisher=

    2023

  53. [68]

    2016 , publisher=

    Tail non-exchangeability , author=. 2016 , publisher=

    2016

  54. [69]

    arXiv preprint arXiv:2206.04248 , year=

    On Lock-down Control of a Pandemic Model , author=. arXiv preprint arXiv:2206.04248 , year=

    work page arXiv

  55. [70]

    European Journal of Statistics , volume=

    Consensus as a Nash Equilibrium of a Stochastic Differential Game , author=. European Journal of Statistics , volume=

  56. [71]

    Operations Research Forum , volume=

    Scoring a goal optimally in a soccer game under Liouville-like quantum gravity action , author=. Operations Research Forum , volume=. 2023 , organization=

    2023

  57. [72]

    Effects of water currents on fish migration through a Feynman-type path integral approach under

    Pramanik, Paramahansa , journal=. Effects of water currents on fish migration through a Feynman-type path integral approach under. 2021 , publisher=

    2021

  58. [74]

    SN Business & Economics , volume=

    Optimization of a dynamic profit function using Euclidean path integral , author=. SN Business & Economics , volume=. 2023 , publisher=

    2023

  59. [76]

    bioRxiv , pages=

    Angiotensin II-Angiotensin II Receptor Type 1 Signaling Facilitates Gastric Cancer Metastasis via Kruppel-like Factor 4 Suppression and Tight Junction Breakdown , author=. bioRxiv , pages=. 2026 , publisher=

    2026

  60. [77]

    Analytics , volume=

    PlayMyData: A Statistical Analysis of a Video Game Dataset on Review Scores and Gaming Platforms , author=. Analytics , volume=. 2025 , publisher=

    2025

  61. [79]

    , author=

    On Estimation of Function-on-function Regression Kernels with Brownian Berkson Errors. , author=

  62. [80]

    and Sprague, B.L

    Munsell, M.F. and Sprague, B.L. and Berry, D.A. and Chisholm, G. and Trentham-Dietz, A. , title =. Epidemiol. Rev. , year =

  63. [81]

    and Sherman, R.L

    Kohler, B.A. and Sherman, R.L. and Howlader, N. and Jemal, A. and Ryerson, A.B. and Henry, K.A. and Boscoe, F.P. and Cronin, K.A. and Lake, A. and Noone, A.-M. , title =. J. Natl. Cancer Inst. , year =. doi:10.1093/jnci/djv048 , note =

    work page doi:10.1093/jnci/djv048

  64. [82]

    and Perou, C.M

    Carey, L.A. and Perou, C.M. and Livasy, C.A. and Dressler, L.G. and Cowan, D. and Conway, K. and Karaca, G. and Troester, M.A. and Tse, C.K. and Edmiston, S. , title =. JAMA , year =. doi:10.1001/jama.295.21.2492 , url =

    work page doi:10.1001/jama.295.21.2492

  65. [83]

    and Haddad, D

    Reid, S. and Haddad, D. and Tezak, A. and Weidner, A. and Wang, X. and Mautz, B. and Moore, J. and Cadiz, S. and Zhu, Y. and Zheng, W. , title =. Breast Cancer Research and Treatment , year =. doi:10.1007/s10549-021-06079-z , url =

    work page doi:10.1007/s10549-021-06079-z

  66. [84]

    and Press, M.F

    Gaudet, M.M. and Press, M.F. and Haile, R.W. and Lynch, C.F. and Glaser, S.L. and Schildkraut, J. and Gammon, M.D. and Douglas Thompson, W. and Bernstein, J.L. , title =. Breast Cancer Research and Treatment , year =. doi:10.1007/s10549-011-1382-2 , url =

    work page doi:10.1007/s10549-011-1382-2

  67. [85]

    and Van Asten, K

    Brouckaert, O. and Van Asten, K. and Laenen, A. and Soubry, A. and Smeets, A. and Nevelstreen, I. and Vergote, I. and Wildiers, H. and Paridaens, R. and Van Limbergen, E. , title =. Breast Cancer Research and Treatment , year =. doi:10.1007/s10549-017-4540-9 , url =

    work page doi:10.1007/s10549-017-4540-9

  68. [86]

    and Tyson, M

    Renehan, A.G. and Tyson, M. and Egger, M. and Heller, R.F. and Zwahlen, M. , title =. Lancet , year =. doi:10.1016/S0140-6736(08)60269-X , url =

    work page doi:10.1016/s0140-6736(08)60269-x

  69. [87]

    adults , author=

    Overweight, obesity, and mortality from cancer in a prospectively studied cohort of U.S. adults , author=. New England Journal of Medicine , volume=. 2003 , publisher=

    2003

  70. [88]

    The Lancet , volume=

    Body-mass index and incidence of cancer: a systematic review and meta-analysis of prospective observational studies , author=. The Lancet , volume=. 2008 , publisher=

    2008

  71. [89]

    CA: A Cancer Journal for Clinicians , volume=

    The obesity paradox in cancer: a review , author=. CA: A Cancer Journal for Clinicians , volume=. 2014 , publisher=

    2014

  72. [90]

    American Journal of Preventive Medicine , volume=

    Race/ethnicity, education, and obesity in US adults: A test of the social patterning hypothesis , author=. American Journal of Preventive Medicine , volume=. 2016 , publisher=

    2016

  73. [91]

    The Breast , volume=

    Clinical implications of the intrinsic molecular subtypes of breast cancer , author=. The Breast , volume=. 2015 , publisher=

    2015

  74. [92]

    JAMA , volume=

    Race, breast cancer subtypes, and survival in the Carolina Breast Cancer Study , author=. JAMA , volume=. 2006 , publisher=

    2006

  75. [93]

    Proceedings of the National Academy of Sciences , volume=

    Gene expression patterns of breast carcinomas distinguish tumor subclasses with clinical implications , author=. Proceedings of the National Academy of Sciences , volume=. 2001 , publisher=

    2001

  76. [94]

    Journal of Clinical Oncology , volume=

    Obesity and cancer mechanisms: tumor microenvironment and inflammation , author=. Journal of Clinical Oncology , volume=. 2016 , publisher=

    2016

  77. [95]

    Nature Reviews Endocrinology , volume=

    Obesity and cancer--mechanisms underlying tumour progression and recurrence , author=. Nature Reviews Endocrinology , volume=. 2017 , publisher=

    2017

  78. [96]

    Breast Cancer Research and Treatment , volume=

    Obesity as a risk factor for triple-negative breast cancers: a systematic review and meta-analysis , author=. Breast Cancer Research and Treatment , volume=. 2013 , publisher=

    2013

  79. [97]

    Cancer Epidemiology, Biomarkers & Prevention , volume=

    Body size and risk of luminal, HER2-expressing, and triple-negative breast cancer in postmenopausal women , author=. Cancer Epidemiology, Biomarkers & Prevention , volume=. 2011 , publisher=

    2011

  80. [98]

    Cancer Research , volume=

    Obesity and breast cancer: Weighing the evidence , author=. Cancer Research , volume=. 2015 , publisher=

    2015

Showing first 80 references.