arxiv: 2605.14453 · v1 · submitted 2026-05-14 · 📊 stat.ME

Recognition: no theorem link

Estimating Precision Matrices for High-Dimensional Interval-Valued Data

Zhongfeng Qin , Hao Xu , Wenhao Cui , Wan Tian

Authors on Pith no claims yet

Pith reviewed 2026-05-15 01:57 UTC · model grok-4.3

classification 📊 stat.ME

keywords precision matrixinterval-valued datagraphical lassohigh-dimensional statisticssparsityconsistencydependency structures

0 comments

The pith

Assuming upper and lower interval bounds share the same dependency structure allows consistent estimation of precision matrices via a specialized graphical lasso.

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

The paper develops a method to estimate precision matrices from high-dimensional data in which each observation is recorded as an interval rather than a single number. It proceeds by positing that the upper and lower endpoints of every interval obey the identical conditional dependence pattern and then casts the estimation task as an interval-adapted graphical lasso problem. An efficient solver is supplied together with proofs that the resulting estimator remains sparse and converges to the true precision matrix. The approach matters because many real measurements arrive naturally as ranges, and recovering the underlying dependence network from such data supports applications in finance, biology, and sensor systems.

Core claim

We assume that the upper and lower bounds of the intervals share the same conditional dependency structure, and then formulate the interval graphical lasso optimization objective to estimate the precision matrix. At the optimization level we provide an efficient computational approach, while at the theoretical level we prove the sparsity and consistency of the estimator. Experimental results on simulated studies and real data applications demonstrate the superiority of the proposed method in terms of estimation precision and interpretability.

What carries the argument

The interval graphical lasso optimization objective, which adapts the standard graphical lasso penalty to interval data under the shared upper-lower dependency assumption.

If this is right

The estimator selects only the true non-zero entries of the precision matrix, producing a sparse dependence graph.
As the number of observations grows the estimated matrix converges in probability to the population precision matrix.
The optimization admits an efficient algorithm that scales to high-dimensional interval data.
On both simulated interval data and real interval-valued applications the method yields higher estimation accuracy than point-wise alternatives.

Where Pith is reading between the lines

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

The same shared-structure device could be tested on other forms of set-valued observations such as fuzzy numbers or confidence intervals.
If the assumption holds only approximately, a robust variant that down-weights discrepant bounds might still recover useful sparse graphs.
Sensor networks that report measurement ranges rather than point readings become direct candidates for this estimator.

Load-bearing premise

The upper and lower bounds of each interval share the same conditional dependency structure.

What would settle it

A collection of interval observations in which the conditional dependence graph recovered from the upper bounds differs substantially from the graph recovered from the lower bounds would contradict the shared-structure premise and cause the estimator to lose consistency.

Figures

Figures reproduced from arXiv: 2605.14453 by Hao Xu, Wan Tian, Wenhao Cui, Zhongfeng Qin.

**Figure 1.** Figure 1: We visualized the data of 50 stocks from the Energy sector of the S&P 500 Index during the period from January 1, 2022, to December 31, 2024, including trend charts, covariance matrix heatmaps, and precision matrix heatmaps. The two rows correspond to the daily highest and lowest prices of the stocks, respectively. The second column demonstrates that estimating the covariance matrix based on the highest an… view at source ↗

**Figure 2.** Figure 2: Estimation accuracy versus 𝑝∕𝑛 ratio. Each rows correspond to DGP1, DGP2, and DGP3, respectively [PITH_FULL_IMAGE:figures/full_fig_p007_2.png] view at source ↗

**Figure 3.** Figure 3: Impact of varying interval widths and dimensions on estimation accuracy (𝑛 = 100). 𝑝 = 200, reflecting the inherent difficulty of high-dimensional estimation. Furthermore, the structural complexity of the precision matrix significantly impacts performance. The Band structure consistently yields the lowest errors due to its high sparsity and simple local structure. In contrast, the E-R structure exhibits th… view at source ↗

**Figure 4.** Figure 4: Visual validation of the estimator. Left: Heatmap comparison showing that the estimated precision matrix accurately captures the sparsity pattern of the true matrix. Right: Scree plot comparing the eigenvalues of the estimated and true precision matrices, indicating strong spectral consistency. 5. Real Data Applications To empirically validate the proposed IGL method, we consider the classic portfolio cons… view at source ↗

read the original abstract

In the field of statistical learning and data analysis, estimating precision matrices (i.e., the inverse of covariance matrices) is a critical task, particularly for understanding dependency structures among variables. However, traditional methods often fall short when dealing with high-dimensional interval-valued data, where each observation is represented as an interval rather than a single point. This paper proposes a novel framework for estimating precision matrices in such contexts, addressing the unique challenges posed by the interval nature of the data. Specifically, we assume that the upper and lower bounds of the intervals share the same conditional dependency structure, and then formulate the interval graphical lasso optimization objective to estimate the precision matrix. At the optimization level, we provide an efficient computational approach, while at the theoretical level, we prove the sparsity and consistency of the estimator. Experimental results on simulated studies and real data applications demonstrate the superiority of the proposed method in terms of estimation precision and interpretability.

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.

Desk Editor's Note private letter to a colleague

A direct graphical lasso extension to interval data that stands or falls on the shared upper/lower dependency assumption.

read the letter

This paper adapts the graphical lasso to high-dimensional interval-valued data by assuming the upper and lower bounds of each interval share the same conditional dependency structure. Under that premise they define a single precision matrix estimator, give an efficient solver, and prove sparsity plus consistency. The simulations and real-data examples show it recovers edges better than midpoint or naive alternatives. The technical development is straightforward and follows the usual lasso consistency route with the necessary adjustments for intervals. The optimization stays close to the standard form, which keeps the implementation practical. The proofs appear to be standard arguments carried over rather than entirely new machinery. The main limitation is the shared-structure assumption itself. It is required for the consistency result to apply, yet the paper supplies no sensitivity checks or diagnostics for when the bounds have different sparsity patterns. If that assumption is violated even moderately, the estimator targets the wrong quantity and the guarantees do not hold. The experimental section is also light on details about how the interval data were generated and whether performance holds across varying interval widths. This work is aimed at researchers who already encounter interval observations in graphical modeling tasks, such as certain measurement or range-data problems. It is a targeted, incremental extension rather than a broad methodological shift. The citations and math look standard and reproducible on their own terms. I would send it for peer review. The contribution is modest but honest enough to deserve referee time, mainly to verify the proofs and push for more robustness checks around the central assumption.

Referee Report

2 major / 2 minor

Summary. The paper proposes a framework for estimating precision matrices from high-dimensional interval-valued data. It assumes that the upper and lower bounds of each interval share the same conditional dependency structure, formulates an interval graphical lasso objective, provides an efficient solver, proves sparsity and consistency of the resulting estimator, and reports superior performance on simulated and real data relative to standard methods.

Significance. If the shared-structure assumption holds and the proofs are tight, the work supplies a direct, computationally tractable extension of graphical lasso to interval observations. This could be useful in domains that routinely record interval data (e.g., finance, environmental monitoring) and would benefit from the sparsity and consistency guarantees once verified.

major comments (2)

[Abstract and §2] Abstract and §2 (model formulation): the shared conditional-dependency assumption between upper and lower bounds is load-bearing for both the objective and the consistency claim. No sensitivity analysis or alternative formulation is supplied when the assumption is violated (different edge sets for bounds), so it is unclear whether the estimator targets a meaningful quantity under realistic interval data.
[Theoretical results] Theoretical section (sparsity and consistency proofs): the abstract states that proofs are provided, yet the derivation appears to reduce directly to the standard graphical-lasso analysis once the shared-structure premise is imposed. Explicit verification is needed that the interval-valued likelihood does not introduce additional bias terms that would invalidate the usual irrepresentable-condition arguments.

minor comments (2)

[Experiments] Experimental section: simulation settings (dimension, interval width distribution, noise level) and real-data preprocessing steps are only sketched; full replication code or detailed tables would strengthen credibility.
[Notation] Notation: the mapping from interval observations to the single precision matrix should be written explicitly (e.g., how the sample covariance is constructed from bounds) to avoid ambiguity in the optimization problem.

Simulated Author's Rebuttal

2 responses · 0 unresolved

We thank the referee for the constructive comments on our manuscript. We address each major point below and have revised the manuscript to incorporate additional analysis and expanded theoretical details where appropriate.

read point-by-point responses

Referee: [Abstract and §2] Abstract and §2 (model formulation): the shared conditional-dependency assumption between upper and lower bounds is load-bearing for both the objective and the consistency claim. No sensitivity analysis or alternative formulation is supplied when the assumption is violated (different edge sets for bounds), so it is unclear whether the estimator targets a meaningful quantity under realistic interval data.

Authors: We appreciate this observation. The shared-structure assumption is central to the proposed framework because it enables pooling of information across bounds to estimate a single precision matrix. In the revised version we will add a dedicated simulation study that evaluates estimator performance under controlled violations of the assumption (specifically, when the edge sets for the upper and lower bounds differ by a small number of edges). We will also insert a short discussion in §2 outlining possible extensions to heterogeneous structures. These additions will clarify the robustness of the method under realistic departures from the core assumption. revision: yes
Referee: [Theoretical results] Theoretical section (sparsity and consistency proofs): the abstract states that proofs are provided, yet the derivation appears to reduce directly to the standard graphical-lasso analysis once the shared-structure premise is imposed. Explicit verification is needed that the interval-valued likelihood does not introduce additional bias terms that would invalidate the usual irrepresentable-condition arguments.

Authors: Thank you for this comment. Although the proofs leverage the standard graphical-lasso analysis once the shared-structure assumption is imposed, we have explicitly derived the interval-valued likelihood and verified that it does not introduce extra bias terms that would invalidate the irrepresentable-condition arguments. In the revision we will expand the theoretical section with a step-by-step derivation that isolates the contribution of the interval likelihood and confirms that the usual irrepresentable condition continues to hold without modification. revision: yes

Circularity Check

0 steps flagged

No significant circularity; modeling assumption is explicit premise

full rationale

The paper states an explicit modeling assumption that upper and lower interval bounds share the same conditional dependency structure, then constructs the interval graphical lasso objective from this premise and derives sparsity/consistency results under it. This is a standard assumption-driven derivation with no reduction of the claimed estimator or theorems to fitted quantities by construction, no self-citation load-bearing steps, and no self-definitional loops in the provided abstract and description. The chain remains self-contained against external benchmarks once the assumption is granted.

Axiom & Free-Parameter Ledger

0 free parameters · 1 axioms · 0 invented entities

The central claim rests on the domain assumption that interval bounds share the same conditional dependency structure plus standard high-dimensional consistency conditions for lasso-type estimators.

axioms (1)

domain assumption Upper and lower bounds of the intervals share the same conditional dependency structure
Explicitly stated in the abstract as the modeling premise that allows a single precision matrix to be estimated.

pith-pipeline@v0.9.0 · 5453 in / 1078 out tokens · 36399 ms · 2026-05-15T01:57:17.072395+00:00 · methodology

discussion (0)

Reference graph

Works this paper leans on

129 extracted references · 129 canonical work pages

[1]

Essays in honor of Aman Ullah , volume=

A vector autoregressive moving average model for interval-valued time series data , author=. Essays in honor of Aman Ullah , volume=. 2016 , publisher=

work page 2016
[2]

2004 , month = feb, publisher =

Olivier Ledoit and Michael Wolf , title =. 2004 , month = feb, publisher =. doi:10.1016/s0047-259x(03)00096-4 , url =

work page doi:10.1016/s0047-259x(03)00096-4 2004
[3]

Journal of the American Statistical Association , volume=

From the statistics of data to the statistics of knowledge: symbolic data analysis , author=. Journal of the American Statistical Association , volume=. 2003 , publisher=

work page 2003
[4]

Econometric Reviews , year=

Interval estimation: an info-metrics approach , author=. Econometric Reviews , year=

work page
[5]

Journal of Business & Economic Statistics , volume=

Constrained regression for interval-valued data , author=. Journal of Business & Economic Statistics , volume=. 2013 , publisher=

work page 2013
[6]

Journal of Money, Credit and Banking , pages=

Forecasting financial volatilities with extreme values: the conditional autoregressive range (CARR) model , author=. Journal of Money, Credit and Banking , pages=. 2005 , publisher=

work page 2005
[7]

Journal of the American statistical association , volume=

Least median of squares regression , author=. Journal of the American statistical association , volume=. 1984 , publisher=

work page 1984
[8]

Mathematical statistics and applications , volume=

Multivariate estimation with high breakdown point , author=. Mathematical statistics and applications , volume=

work page
[9]

Technometrics , volume=

Robust estimates of location and dispersion for high-dimensional datasets , author=. Technometrics , volume=. 2002 , publisher=

work page 2002
[10]

2012 , institution=

Regularized Minimum Covariance Determinant estimator , author=. 2012 , institution=

work page 2012
[11]

Statistics and Computing , volume=

The minimum regularized covariance determinant estimator , author=. Statistics and Computing , volume=. 2020 , publisher=

work page 2020
[12]

The Annals of statistics , volume=

Covariance regularization by thresholding , author=. The Annals of statistics , volume=. 2008 , publisher=

work page 2008
[13]

The Annals of statistics , volume=

Sparsistency and rates of convergence in large covariance matrix estimation , author=. The Annals of statistics , volume=. 2009 , publisher=

work page 2009
[14]

The Annals of Statistics , volume=

The spectrum of kernel random matrices , author=. The Annals of Statistics , volume=. 2010 , publisher=

work page 2010
[15]

The Econometrics Journal , volume=

An overview of the estimation of large covariance and precision matrices , author=. The Econometrics Journal , volume=. 2016 , publisher=

work page 2016
[16]

Wiley Interdisciplinary Reviews: Computational Statistics , volume=

Minimum volume ellipsoid , author=. Wiley Interdisciplinary Reviews: Computational Statistics , volume=. 2009 , publisher=

work page 2009
[17]

Technometrics , volume=

A fast algorithm for the minimum covariance determinant estimator , author=. Technometrics , volume=. 1999 , publisher=

work page 1999
[18]

Wiley StatsRef: Statistics Reference Online , pages=

Robust estimation of multivariate location and scatter , author=. Wiley StatsRef: Statistics Reference Online , pages=. 2014 , publisher=

work page 2014
[19]

Extension de l'analyse en composantes principales

Cazes, Pierre and Chouakria, Ahlame and Diday, Edwin and Schektman, Yves , journal=. Extension de l'analyse en composantes principales

work page
[20]

2012 , publisher=

Wang, Huiwen and Guan, Rong and Wu, Junjie , journal=. 2012 , publisher=

work page 2012
[21]

International encyclopedia of statistical science , pages=

Robust statistics , author=. International encyclopedia of statistical science , pages=. 2011 , publisher=

work page 2011
[22]

The Annals of Statistics , pages=

Asymptotics for the minimum covariance determinant estimator , author=. The Annals of Statistics , pages=. 1993 , publisher=

work page 1993
[23]

Bernoulli , volume=

Central limit theorem and influence function for the MCD estimators at general multivariate distributions , author=. Bernoulli , volume=. 2012 , publisher=

work page 2012
[24]

Journal of Multivariate Analysis , volume=

Influence function and efficiency of the minimum covariance determinant scatter matrix estimator , author=. Journal of Multivariate Analysis , volume=. 1999 , publisher=

work page 1999
[25]

The Annals of Statistics , pages=

Breakdown points of affine equivariant estimators of multivariate location and covariance matrices , author=. The Annals of Statistics , pages=. 1991 , publisher=

work page 1991
[26]

2005 , publisher=

Robust regression and outlier detection , author=. 2005 , publisher=

work page 2005
[27]

Analysis of symbolic data , pages=

Descriptive statistics for symbolic data , author=. Analysis of symbolic data , pages=. 2000 , publisher=

work page 2000
[28]

Proceedings of World IASC Conference, Yokohama, Japan , pages=

Sample covariance functions for complex quantitative data , author=. Proceedings of World IASC Conference, Yokohama, Japan , pages=

work page
[29]

A Festschrift for Erich L

The notion of breakdown point , author=. A Festschrift for Erich L. Lehmann , year=

work page
[30]

Journal of Multivariate Analysis , volume=

The multivariate least-trimmed squares estimator , author=. Journal of Multivariate Analysis , volume=. 2008 , publisher=

work page 2008
[31]

Wiley interdisciplinary reviews: Computational statistics , volume=

Minimum covariance determinant , author=. Wiley interdisciplinary reviews: Computational statistics , volume=. 2010 , publisher=

work page 2010
[32]

Journal of Statistical Software , author=

An Object-Oriented Framework for Robust Multivariate Analysis , volume=. Journal of Statistical Software , author=. 2009 , pages=

work page 2009
[33]

and Chouakria, A

Cazes, P. and Chouakria, A. and Diday, E. and Schektman, Y. , title =. Revue de Statistique Appliqu\'ee , pages =. 1997 , language =

work page 1997
[34]

Zhang and M

J. Zhang and M. Liu and M. Dong , title =. 2019 , month = jan, publisher =. doi:10.1016/j.neucom.2018.09.083 , url =

work page doi:10.1016/j.neucom.2018.09.083 2019
[35]

Ogata and S

H. Ogata and S. Goto and K. Sato and W. Fujibuchi and H. Bono and M. Kanehisa , title =. 1999 , month = jan, publisher =. doi:10.1093/nar/27.1.29 , url =

work page doi:10.1093/nar/27.1.29 1999
[36]

2015 , month = apr, publisher =

Ernst C Wit and Antonino Abbruzzo , title =. 2015 , month = apr, publisher =. doi:10.1186/1471-2105-16-s6-s5 , url =

work page doi:10.1186/1471-2105-16-s6-s5 2015
[37]

2018 , month = mar, publisher =

Marco Avella-Medina and Heather S Battey and Jianqing Fan and Quefeng Li , title =. 2018 , month = mar, publisher =. doi:10.1093/biomet/asy011 , url =

work page doi:10.1093/biomet/asy011 2018
[38]

Pope and Pan Du and Simon Lin and Nalini M

Chiang-Ching Huang and Kiang Liu and Richard M. Pope and Pan Du and Simon Lin and Nalini M. Rajamannan and Qi-Quan Huang and Nadereh Jafari and Gregory L. Burke and Wendy Post and Karol E.Watson and Craig Johnson and Martha L. Daviglus and Donald M. Lloyd-Jones , editor =. Activated. 2011 , month = jun, publisher =. doi:10.1371/journal.pone.0021067 , url =

work page doi:10.1371/journal.pone.0021067 2011
[39]

Biostatistics , volume=

Sparse inverse covariance estimation with the graphical lasso , author=. Biostatistics , volume=. 2008 , publisher=

work page 2008
[40]

2011 , publisher=

Statistics for high-dimensional data: methods, theory and applications , author=. 2011 , publisher=

work page 2011
[41]

Annals of Statistics , year=

Least angle regression , author=. Annals of Statistics , year=

work page
[42]

European Journal of Operational Research , volume=

Model averaging for interval-valued data , author=. European Journal of Operational Research , volume=. 2022 , publisher=

work page 2022
[43]

The Annals of Statistics , pages=

Estimating regression parameters using linear rank tests for censored data , author=. The Annals of Statistics , pages=. 1990 , publisher=

work page 1990
[44]

The Annals of Mathematical Statistics , volume=

The distribution of linear combinations of order statistics from the uniform distribution , author=. The Annals of Mathematical Statistics , volume=. 1971 , publisher=

work page 1971
[45]

Asymptotic behaviour of

Davies, P Laurie , journal=. Asymptotic behaviour of. 1987 , publisher=

work page 1987
[46]

Zuo, Yijun and Cui, Hengjian and He, Xuming , journal=. On the. 2004 , publisher=

work page 2004
[47]

Constrained

Kent, John T and Tyler, David E , journal=. Constrained. 1996 , publisher=

work page 1996
[48]

On the uniqueness of

Tatsuoka, Kay S and Tyler, David E , journal=. On the uniqueness of. 2000 , publisher=

work page 2000
[49]

1958 , publisher=

An introduction to multivariate statistical analysis , author=. 1958 , publisher=

work page 1958
[50]

Biometrika , volume=

Nonparametric estimation of large covariance matrices of longitudinal data , author=. Biometrika , volume=. 2003 , publisher=

work page 2003
[51]

Annals of Statistics , year=

Regularized estimation of large covariance matrices , author=. Annals of Statistics , year=

work page
[52]

Journal of Multivariate Analysis , year=

Estimation of high-dimensional prior and posterior covariance matrices in Kalman filter variants , author=. Journal of Multivariate Analysis , year=

work page
[53]

Annals of Statistics , year=

Optimal rates of convergence for covariance matrix estimation , author=. Annals of Statistics , year=

work page
[54]

Statistics and Computing , volume=

The minimum covariance determinant estimator for interval-valued data , author=. Statistics and Computing , volume=. 2024 , publisher=

work page 2024
[55]

Statistics and Computing , volume=

IDGM: an approach to estimate the graphical model of interval-valued data , author=. Statistics and Computing , volume=. 2024 , publisher=

work page 2024
[56]

Data analysis, classification, and related methods , pages=

Regression analysis for interval-valued data , author=. Data analysis, classification, and related methods , pages=. 2000 , publisher=

work page 2000
[57]

Pattern Analysis and Applications , volume=

Nonlinear regression applied to interval-valued data , author=. Pattern Analysis and Applications , volume=. 2017 , publisher=

work page 2017
[58]

Wiley Interdisciplinary Reviews: Computational Statistics , volume=

Linear regression with interval-valued data , author=. Wiley Interdisciplinary Reviews: Computational Statistics , volume=. 2016 , publisher=

work page 2016
[59]

Neurocomputing , volume=

Forecasting models for interval-valued time series , author=. Neurocomputing , volume=. 2008 , publisher=

work page 2008
[60]

International Journal of Forecasting , volume=

Holt’s exponential smoothing and neural network models for forecasting interval-valued time series , author=. International Journal of Forecasting , volume=. 2011 , publisher=

work page 2011
[61]

Journal of Econometrics , volume=

Threshold autoregressive models for interval-valued time series data , author=. Journal of Econometrics , volume=. 2018 , publisher=

work page 2018
[62]

Journal of Computational and Graphical Statistics , volume=

Symbolic covariance principal component analysis and visualization for interval-valued data , author=. Journal of Computational and Graphical Statistics , volume=. 2012 , publisher=

work page 2012
[63]

Journal of Computational and Graphical Statistics , volume=

Visualization for interval data , author=. Journal of Computational and Graphical Statistics , volume=. 2022 , publisher=

work page 2022
[64]

The Annals of Statistics , pages=

NEARLY UNBIASED VARIABLE SELECTION UNDER MINIMAX CONCAVE PENALTY , author=. The Annals of Statistics , pages=. 2010 , publisher=

work page 2010
[65]

Journal of the American statistical Association , volume=

Variable selection via nonconcave penalized likelihood and its oracle properties , author=. Journal of the American statistical Association , volume=. 2001 , publisher=

work page 2001
[66]

Wainwright and Garvesh Raskutti and Bin Yu , title =

Pradeep Ravikumar and Martin J. Wainwright and Garvesh Raskutti and Bin Yu , title =. Electronic Journal of Statistics , pages =

work page
[67]

Rothman and Peter J

Adam J. Rothman and Peter J. Bickel and Elizaveta Levina and Ji Zhu , title =. Electronic Journal of Statistics , pages =

work page
[68]

The Journal of Machine Learning Research , volume=

Model selection through sparse maximum likelihood estimation for multivariate Gaussian or binary data , author=. The Journal of Machine Learning Research , volume=. 2008 , publisher=

work page 2008
[69]

The review of Financial studies , volume=

Optimal versus naive diversification: How inefficient is the 1/N portfolio strategy? , author=. The review of Financial studies , volume=. 2009 , publisher=

work page 2009
[70]

The Journal of Finance , volume=

Range-based estimation of stochastic volatility models , author=. The Journal of Finance , volume=. 2002 , publisher=

work page 2002
[71]

Journal of multivariate analysis , volume=

A well-conditioned estimator for large-dimensional covariance matrices , author=. Journal of multivariate analysis , volume=. 2004 , publisher=

work page 2004
[72]

Proceedings of the National Academy of Sciences , volume=

Sparse and stable Markowitz portfolios , author=. Proceedings of the National Academy of Sciences , volume=. 2009 , publisher=

work page 2009
[73]

The Review of Financial Studies , volume=

Approaching mean-variance efficiency for large portfolios , author=. The Review of Financial Studies , volume=. 2019 , publisher=

work page 2019
[74]

Journal of the American Statistical Association , volume=

Vast volatility matrix estimation using high-frequency data for portfolio selection , author=. Journal of the American Statistical Association , volume=. 2012 , publisher=

work page 2012
[75]

Journal of financial economics , volume=

Markowitz meets Talmud: A combination of sophisticated and naive diversification strategies , author=. Journal of financial economics , volume=. 2011 , publisher=

work page 2011
[76]

Bioinformatics , volume=

An empirical Bayes approach to inferring large-scale gene association networks , author=. Bioinformatics , volume=. 2005 , publisher=

work page 2005
[77]

Journal of Financial Economics , volume=

In-sample and out-of-sample Sharpe ratios of multi-factor asset pricing models , author=. Journal of Financial Economics , volume=. 2024 , publisher=

work page 2024
[78]

Journal of Econometrics , volume=

High dimensional covariance matrix estimation using a factor model , author=. Journal of Econometrics , volume=. 2008 , publisher=

work page 2008
[79]

Journal of the Royal Statistical Society Series B: Statistical Methodology , volume=

Large covariance estimation by thresholding principal orthogonal complements , author=. Journal of the Royal Statistical Society Series B: Statistical Methodology , volume=. 2013 , publisher=

work page 2013
[80]

2003 , publisher=

A no-arbitrage approach to range-based estimation of return covariances and correlations , author=. 2003 , publisher=

work page 2003

Showing first 80 references.