IDEAS home Printed from https://ideas.repec.org/a/eee/csdana/v171y2022ics0167947322000391.html
   My bibliography  Save this article

Asymptotic covariance estimation by Gaussian random perturbation

Author

Listed:
  • Zhou, Jing
  • Lan, Wei
  • Wang, Hansheng

Abstract

In most cases, the asymptotic covariance matrix of an M-estimator is in a sandwich form. This sandwich form involves calculations of the first and second order derivatives of the loss function, which is intractable if the loss function is complex. To alleviate this problem, we propose in this article a novel method called Gaussian random perturbation. This method can be used to estimate the asymptotic covariance matrix of a general M-estimator without derivative calculations. The idea can be summarized as follows. We first generate a small random perturbation around the M-estimator. Then, we re-evaluate the loss function at the randomly perturbed M-estimator and obtain the estimators of the first and second order derivatives of the loss function via Taylor series expansion. This leads to a novel estimator for the asymptotic covariance matrix. We then rigorously show that the resulting covariance estimator is statistically consistent with two elegant characteristics. First, it involves no computation of derivatives. This makes it easier to estimate the covariance matrix of an M-estimator with a complex loss function. Second, it is convenient for parallel computing and thus attractive for massive data analysis. The consistency of the proposed asymptotic covariance estimator is demonstrated under appropriate regularity conditions. The practical usefulness of the method is further demonstrated with both simulation studies and real data analysis.

Suggested Citation

  • Zhou, Jing & Lan, Wei & Wang, Hansheng, 2022. "Asymptotic covariance estimation by Gaussian random perturbation," Computational Statistics & Data Analysis, Elsevier, vol. 171(C).
  • Handle: RePEc:eee:csdana:v:171:y:2022:i:c:s0167947322000391
    DOI: 10.1016/j.csda.2022.107459
    as

    Download full text from publisher

    File URL: http://www.sciencedirect.com/science/article/pii/S0167947322000391
    Download Restriction: Full text for ScienceDirect subscribers only.

    File URL: https://libkey.io/10.1016/j.csda.2022.107459?utm_source=ideas
    LibKey link: if access is restricted and if your library uses this service, LibKey will redirect you to where you can use your library subscription to access this item
    ---><---

    As the access to this document is restricted, you may want to search for a different version of it.

    References listed on IDEAS

    as
    1. Jeffrey M. Wooldridge, 2001. "Applications of Generalized Method of Moments Estimation," Journal of Economic Perspectives, American Economic Association, vol. 15(4), pages 87-100, Fall.
    2. Chen, Kani & Guo, Shaojun & Lin, Yuanyuan & Ying, Zhiliang, 2010. "Least Absolute Relative Error Estimation," Journal of the American Statistical Association, American Statistical Association, vol. 105(491), pages 1104-1112.
    3. Jing Zhou & Jin Liu & Feifei Wang & Hansheng Wang, 2022. "Autoregressive Model With Spatial Dependence and Missing Data," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 40(1), pages 28-34, January.
    4. Jiwei Zhao & Jun Shao, 2015. "Semiparametric Pseudo-Likelihoods in Generalized Linear Models With Nonignorable Missing Data," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 110(512), pages 1577-1590, December.
    5. Joseph Ibrahim & Geert Molenberghs, 2009. "Missing data methods in longitudinal studies: a review," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 18(1), pages 1-43, May.
    6. Xuerong Chen & Alan T. K. Wan & Yong Zhou, 2015. "Efficient Quantile Regression Analysis With Missing Observations," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 110(510), pages 723-741, June.
    7. Shao J. & Wang H., 2002. "Sample Correlation Coefficients Based on Survey Data Under Regression Imputation," Journal of the American Statistical Association, American Statistical Association, vol. 97, pages 544-552, June.
    8. Joseph Ibrahim & Geert Molenberghs, 2009. "Rejoinder on: Missing data methods in longitudinal studies: a review," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 18(1), pages 68-75, May.
    9. Qihua Wang & Pengjie Dai, 2008. "Semiparametric model-based inference in the presence of missing responses," Biometrika, Biometrika Trust, vol. 95(3), pages 721-734.
    10. Huazhen Lin & Wei Liu & Wei Lan, 2021. "Regression Analysis with Individual-Specific Patterns of Missing Covariates," Journal of Business & Economic Statistics, Taylor & Francis Journals, vol. 39(1), pages 179-188, January.
    Full references (including those not matched with items on IDEAS)

    Most related items

    These are the items that most often cite the same works as this one and are cited by the same works as this one.
    1. Wan-Lun Wang, 2019. "Mixture of multivariate t nonlinear mixed models for multiple longitudinal data with heterogeneity and missing values," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 28(1), pages 196-222, March.
    2. Maria Gheorghe & Susan Picavet & Monique Verschuren & Werner B. F. Brouwer & Pieter H. M. Baal, 2017. "Health losses at the end of life: a Bayesian mixed beta regression approach," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 180(3), pages 723-749, June.
    3. Cai, T. Tony & Zhang, Anru, 2016. "Minimax rate-optimal estimation of high-dimensional covariance matrices with incomplete data," Journal of Multivariate Analysis, Elsevier, vol. 150(C), pages 55-74.
    4. Jouni Kuha & Myrsini Katsikatsou & Irini Moustaki, 2018. "Latent variable modelling with non‐ignorable item non‐response: multigroup response propensity models for cross‐national analysis," Journal of the Royal Statistical Society Series A, Royal Statistical Society, vol. 181(4), pages 1169-1192, October.
    5. Li, Chao & Sun, Daoming, 2023. "Women’s bargaining power and spending on children’s education: Evidence from a natural experiment in China," International Journal of Educational Development, Elsevier, vol. 100(C).
    6. Francesco Bravo, 2020. "Robust estimation and inference for general varying coefficient models with missing observations," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 29(4), pages 966-988, December.
    7. Tithi Biswas & Kylie H. Kang & Rohin Gawdi & David Bajor & Mitchell Machtay & Charu Jindal & Jimmy T. Efird, 2020. "Using the Systemic Immune-Inflammation Index (SII) as a Mid-Treatment Marker for Survival among Patients with Stage-III Locally Advanced Non-Small Cell Lung Cancer (NSCLC)," IJERPH, MDPI, vol. 17(21), pages 1-13, October.
    8. D. Claire Miller & Samantha MaWhinney & Jennifer L. Patnaik & Karen L. Christopher & Anne M. Lynch & Brandie D. Wagner, 2022. "Predictors of refraction prediction error after cataract surgery: a shared parameter model to account for missing post-operative measurements," Statistical Methods & Applications, Springer;Società Italiana di Statistica, vol. 31(2), pages 343-364, June.
    9. Weiping Zhang & Feiyue Xie & Jiaxin Tan, 2020. "A robust joint modeling approach for longitudinal data with informative dropouts," Computational Statistics, Springer, vol. 35(4), pages 1759-1783, December.
    10. An-Min Tang & Nian-Sheng Tang & Dalei Yu, 2023. "Bayesian semiparametric joint model of multivariate longitudinal and survival data with dependent censoring," Lifetime Data Analysis: An International Journal Devoted to Statistical Methods and Applications for Time-to-Event Data, Springer, vol. 29(4), pages 888-918, October.
    11. Nanhua Zhang & Henian Chen & Yuanshu Zou, 2014. "A joint model of binary and longitudinal data with non-ignorable missingness, with application to marital stress and late-life major depression in women," Journal of Applied Statistics, Taylor & Francis Journals, vol. 41(5), pages 1028-1039, May.
    12. Daniel O. Scharfstein & Jon Steingrimsson & Aidan McDermott & Chenguang Wang & Souvik Ray & Aimee Campbell & Edward Nunes & Abigail Matthews, 2022. "Global sensitivity analysis of randomized trials with nonmonotone missing binary outcomes: Application to studies of substance use disorders," Biometrics, The International Biometric Society, vol. 78(2), pages 649-659, June.
    13. Antonello Maruotti, 2015. "Handling non-ignorable dropouts in longitudinal data: a conditional model based on a latent Markov heterogeneity structure," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 24(1), pages 84-109, March.
    14. Li, Xiaofei & Huebner, E. Scott & Tian, Lili, 2021. "Vicious cycle of emotional maltreatment and bullying perpetration/victimization among early adolescents: Depressive symptoms as a mediator," Social Science & Medicine, Elsevier, vol. 291(C).
    15. Xuerong Chen & Guoqing Diao & Jing Qin, 2020. "Pseudo likelihood‐based estimation and testing of missingness mechanism function in nonignorable missing data problems," Scandinavian Journal of Statistics, Danish Society for Theoretical Statistics;Finnish Statistical Society;Norwegian Statistical Association;Swedish Statistical Association, vol. 47(4), pages 1377-1400, December.
    16. Shaikh, Ibrahim A. & O'Brien, Jonathan Paul & Peters, Lois, 2018. "Inside directors and the underinvestment of financial slack towards R&D-intensity in high-technology firms," Journal of Business Research, Elsevier, vol. 82(C), pages 192-201.
    17. de Mendonça, Helder Ferreira & Tiberto, Bruno Pires, 2014. "Public debt and social security: Level of formality matters," Economic Modelling, Elsevier, vol. 42(C), pages 490-507.
    18. Roberto Martino & Phu Nguyen-Van, 2014. "Labour market regulation and fiscal parameters: A structural model for European regions," Working Papers of BETA 2014-19, Bureau d'Economie Théorique et Appliquée, UDS, Strasbourg.
    19. Ongo Nkoa, Bruno Emmanuel & Song, Jacques Simon, 2020. "Does institutional quality affect financial inclusion in Africa? A panel data analysis," Economic Systems, Elsevier, vol. 44(4).
    20. Oukhallou, Youssef, 2019. "Military Expenditure and Economic Development," MPRA Paper 98352, University Library of Munich, Germany.

    Corrections

    All material on this site has been provided by the respective publishers and authors. You can help correct errors and omissions. When requesting a correction, please mention this item's handle: RePEc:eee:csdana:v:171:y:2022:i:c:s0167947322000391. See general information about how to correct material in RePEc.

    If you have authored this item and are not yet registered with RePEc, we encourage you to do it here. This allows to link your profile to this item. It also allows you to accept potential citations to this item that we are uncertain about.

    If CitEc recognized a bibliographic reference but did not link an item in RePEc to it, you can help with this form .

    If you know of missing items citing this one, you can help us creating those links by adding the relevant references in the same way as above, for each refering item. If you are a registered author of this item, you may also want to check the "citations" tab in your RePEc Author Service profile, as there may be some citations waiting for confirmation.

    For technical questions regarding this item, or to correct its authors, title, abstract, bibliographic or download information, contact: Catherine Liu (email available below). General contact details of provider: http://www.elsevier.com/locate/csda .

    Please note that corrections may take a couple of weeks to filter through the various RePEc services.

    IDEAS is a RePEc service. RePEc uses bibliographic data supplied by the respective publishers.