IDEAS home Printed from https://ideas.repec.org/a/wly/navres/v53y2006i4p261-271.html
   My bibliography  Save this article

A mathematical programming approach for improving the robustness of least sum of absolute deviations regression

Author

Listed:
  • Avi Giloni
  • Bhaskar Sengupta
  • Jeffrey S. Simonoff

Abstract

This paper discusses a novel application of mathematical programming techniques to a regression problem. While least squares regression techniques have been used for a long time, it is known that their robustness properties are not desirable. Specifically, the estimators are known to be too sensitive to data contamination. In this paper we examine regressions based on Least‐sum of Absolute Deviations (LAD) and show that the robustness of the estimator can be improved significantly through a judicious choice of weights. The problem of finding optimum weights is formulated as a nonlinear mixed integer program, which is too difficult to solve exactly in general. We demonstrate that our problem is equivalent to a mathematical program with a single functional constraint resembling the knapsack problem and then solve it for a special case. We then generalize this solution to general regression designs. Furthermore, we provide an efficient algorithm to solve the general nonlinear, mixed integer programming problem when the number of predictors is small. We show the efficacy of the weighted LAD estimator using numerical examples. © 2006 Wiley Periodicals, Inc. Naval Research Logistics, 2006

Suggested Citation

  • Avi Giloni & Bhaskar Sengupta & Jeffrey S. Simonoff, 2006. "A mathematical programming approach for improving the robustness of least sum of absolute deviations regression," Naval Research Logistics (NRL), John Wiley & Sons, vol. 53(4), pages 261-271, June.
    • Handle: RePEc:wly:navres:v:53:y:2006:i:4:p:261-271
    DOI: 10.1002/nav.20139
    as

    Download full text from publisher

    File URL: https://doi.org/10.1002/nav.20139
    Download Restriction: no
    File URL: https://libkey.io/10.1002/nav.20139?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
    ---><---

    References listed on IDEAS

    as
    1. He, Xuming, et al, 1990. "Tail Behavior of Regression Estimators and Their Breakdown Points," Econometrica, Econometric Society, vol. 58(5), pages 1195-1214, September.
    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. Vijverberg, Wim P. & Hasebe, Takuya, 2015. "GTL Regression: A Linear Model with Skewed and Thick-Tailed Disturbances," IZA Discussion Papers 8898, Institute of Labor Economics (IZA).
    2. Jurecková, Jana, 2010. "Finite-sample distribution of regression quantiles," Statistics & Probability Letters, Elsevier, vol. 80(23-24), pages 1940-1946, December.
    3. Tamara Broderick & Ryan Giordano & Rachael Meager, 2020. "An Automatic Finite-Sample Robustness Metric: When Can Dropping a Little Data Make a Big Difference?," Papers 2011.14999, arXiv.org, revised Jul 2023.
    4. Jurecková, Jana, 2000. "Test of tails based on extreme regression quantiles," Statistics & Probability Letters, Elsevier, vol. 49(1), pages 53-61, August.
    5. Neykov, N.M. & Čížek, P. & Filzmoser, P. & Neytchev, P.N., 2012. "The least trimmed quantile regression," Computational Statistics & Data Analysis, Elsevier, vol. 56(6), pages 1757-1770.
    6. Davies, P. Laurie & Fried, Roland & Gather, Ursula, 2002. "Robust signal extraction for on-line monitoring data," Technical Reports 2002,02, Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen.
    7. Hill, Jonathan B. & Aguilar, Mike, 2013. "Moment condition tests for heavy tailed time series," Journal of Econometrics, Elsevier, vol. 172(2), pages 255-274.
    8. Jurecková, Jana & Koenker, Roger & Portnoy, Stephen, 2001. "Tail behavior of the least-squares estimator," Statistics & Probability Letters, Elsevier, vol. 55(4), pages 377-384, December.
    9. Salvador Flores, 2015. "Sharp non-asymptotic performance bounds for $$\ell _1$$ ℓ 1 and Huber robust regression estimators," TEST: An Official Journal of the Spanish Society of Statistics and Operations Research, Springer;Sociedad de Estadística e Investigación Operativa, vol. 24(4), pages 796-812, December.
    10. Čížek, Pavel, 2012. "Semiparametric robust estimation of truncated and censored regression models," Journal of Econometrics, Elsevier, vol. 168(2), pages 347-366.
    11. Ke Zhu & Shiqing Ling, 2015. "LADE-Based Inference for ARMA Models With Unspecified and Heavy-Tailed Heteroscedastic Noises," Journal of the American Statistical Association, Taylor & Francis Journals, vol. 110(510), pages 784-794, June.
    12. Mikosch, Thomas & de Vries, Casper G., 2013. "Heavy tails of OLS," Journal of Econometrics, Elsevier, vol. 172(2), pages 205-221.
    13. Jozef Kušnier & Ivan Mizera, 2001. "Tail Behavior and Breakdown Properties of Equivariant Estimators of Location," Annals of the Institute of Statistical Mathematics, Springer;The Institute of Statistical Mathematics, vol. 53(2), pages 244-261, June.
    14. Cizek, P., 2009. "Generalized Methods of Trimmed Moments," Discussion Paper 2009-25, Tilburg University, Center for Economic Research.
    15. Gather, Ursula & Einbeck, Jochen & Fried, Roland, 2005. "Weighted Repeated Median Smoothing and Filtering," Technical Reports 2005,33, Technische Universität Dortmund, Sonderforschungsbereich 475: Komplexitätsreduktion in multivariaten Datenstrukturen.
    16. Hubert, Mia, 1997. "The breakdown value of the L1 estimator in contingency tables," Statistics & Probability Letters, Elsevier, vol. 33(4), pages 419-425, May.
    17. Christine Müller, 2011. "Data depth for simple orthogonal regression with application to crack orientation," Metrika: International Journal for Theoretical and Applied Statistics, Springer, vol. 74(2), pages 135-165, September.
    18. Mizera, Ivan & Müller, Christine H., 2002. "Breakdown points of Cauchy regression-scale estimators," Statistics & Probability Letters, Elsevier, vol. 57(1), pages 79-89, March.
    19. Barbe, Ph. & Broniatowski, M., 2004. "Blowing number of a distribution for a statistics and loyal estimators," Statistics & Probability Letters, Elsevier, vol. 69(4), pages 465-475, October.
    20. Giloni, Avi & Simonoff, Jeffrey S. & Sengupta, Bhaskar, 2006. "Robust weighted LAD regression," Computational Statistics & Data Analysis, Elsevier, vol. 50(11), pages 3124-3140, July.

    More about this item

    Statistics

    Access and download statistics

    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:wly:navres:v:53:y:2006:i:4:p:261-271. 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: Wiley Content Delivery (email available below). General contact details of provider: https://doi.org/10.1002/(ISSN)1520-6750 .

    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.