1. bookVolume 20 (2020): Issue 1 (February 2020)
Journal Details
License
Format
Journal
eISSN
1335-8871
First Published
07 Mar 2008
Publication timeframe
6 times per year
Languages
English
access type Open Access

On Robust Estimation of Error Variance in (Highly) Robust Regression

Published Online: 24 Feb 2020
Volume & Issue: Volume 20 (2020) - Issue 1 (February 2020)
Page range: 6 - 14
Received: 10 Sep 2019
Accepted: 25 Jan 2020
Journal Details
License
Format
Journal
eISSN
1335-8871
First Published
07 Mar 2008
Publication timeframe
6 times per year
Languages
English
Abstract

The linear regression model requires robust estimation of parameters, if the measured data are contaminated by outlying measurements (outliers). While a number of robust estimators (i.e. resistant to outliers) have been proposed, this paper is focused on estimating the variance of the random regression errors. We particularly focus on the least weighted squares estimator, for which we review its properties and propose new weighting schemes together with corresponding estimates for the variance of disturbances. An illustrative example revealing the idea of the estimator to down-weight individual measurements is presented. Further, two numerical simulations presented here allow to compare various estimators. They verify the theoretical results for the least weighted squares to be meaningful. MM-estimators turn out to yield the best results in the simulations in terms of both accuracy and precision. The least weighted squares (with suitable weights) remain only slightly behind in terms of the mean square error and are able to outperform the much more popular least trimmed squares estimator, especially for smaller sample sizes.

Keywords

[1] Hald A. (2006). A history of parametric statistical inference from Bernoulli to Fisher, 1713 to 1935. New York: Springer.Search in Google Scholar

[2] Dietrich, C.F. (1991). Uncertainty, calibration and probability. The statistics of scientific and industrial measurement. 2nd edn. Boca Raton: Taylor & Francis.Search in Google Scholar

[3] Neykov, N., Filzmoser, P., Dimova, R., & Neytchev, P. (2007). Robust fitting of mixtures using the trimmed likelihood estimator. Computational Statistics & Data Analysis, 52, 299–308.10.1016/j.csda.2006.12.024Search in Google Scholar

[4] White, G.H. (2008). Basics of estimating measurement uncertainty. Clinical Biochemist Reviews, 29, S53–S60.Search in Google Scholar

[5] Hekimoglu, S., Erenoglu, R.C., & Kalina, J. (2009). Outlier detection by means of robust regression estimators for use in engineering science. Journal of Zhejiang University Science A, 10, 909–921.10.1631/jzus.A0820140Search in Google Scholar

[6] Luukinen J.M., Aalto D., Malinen, J., Niikuni, N., Saunavaara, J., Jääsaari, P., Ojalammi. A., Parkkola, R., Soukka, T., & Happonen, R.P. (2018). A novel marker based method to teeth alignment in MRI. Measurement Science Review, 18, 79–85.10.1515/msr-2018-0012Search in Google Scholar

[7] Kumar, N., Hoque, M.A.,Shahjaman, M., Islam, S.M.S., Mollah, M.N.H. (2017). Metabolomic biomarker identification in presence of outliers and missing values. BioMed Research International, 2017, Article 2437608.10.1155/2017/2437608533116928293630Search in Google Scholar

[8] Kalina, J. (2018). A robust pre-processing of BeadChip microarray images. Biocybernetics and Biomedical Engineering, 38, 556–563.10.1016/j.bbe.2018.04.005Search in Google Scholar

[9] Jurečková, J., Picek, J., & Schindler, M. (2019). Robust statistical methods with R. 2nd edn. Boca Raton: CRC Press.10.1201/b21993Search in Google Scholar

[10] Rousseeuw, P.J. & Leroy, A.M. (1987). Robust regression and outlier detection. New York: Wiley.10.1002/0471725382Search in Google Scholar

[11] Kalina, J. (2012). Implicitly weighted methods in robust image analysis. Journal of Mathematical Imaging and Vision, 44, 449–462.10.1007/s10851-012-0337-zSearch in Google Scholar

[12] Víšek, J.Á. (2011). Consistency of the least weighted squares under heteroscedasticity. Kybernetika, 47, 179–206.Search in Google Scholar

[13] Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., & Stahel, W.A. (1986). Robust statistics. The approach based on influence functions. New York: Wiley.Search in Google Scholar

[14] Ranganai, E. (2016). On studentized residuals in the quantile regression framework. SpringerPlus, 5, Article 1231.10.1186/s40064-016-2898-6497100127536515Search in Google Scholar

[15] Davies, P.L. & Kovac A. (2001). Local extremes, runs, strings and multiresolution. Annals of Statistics, 29, 1–65.10.1214/aos/996986501Search in Google Scholar

[16] Rousseeuw, P.J. & Hubert, M. (2011). Robust statistics for outlier detection. Wiley Interdisciplinary Reviews: Data Mining and Knowledge Discovery, 1, 73–79.10.1002/widm.2Search in Google Scholar

[17] Davies, L. (1990). The asymptotics of S-estimators in the linear regression model. Annals of Statistics, 18, 1651–1675.10.1214/aos/1176347871Search in Google Scholar

[18] Riani, M., Cerioli, A., & Torti, F. (2014). On consistency factors and efficiency of robust S-estimators. Test, 23, 356–387.10.1007/s11749-014-0357-7Search in Google Scholar

[19] Yohai, V.J. (1987). High breakdown-point and high efficiency robust estimates for regression. Annals of Statistics, 15, 642–656.10.1214/aos/1176350366Search in Google Scholar

[20] Víšek, J.Á. (2006). The least trimmed squares. Part I: Consistency. Kybernetika, 42, 1–36.Search in Google Scholar

[21] Roelant, E., Van Aelst, S., & Willems, G. (2009). The minimum weighted covariance determinant estimator. Metrika, 70, 177–204.10.1007/s00184-008-0186-3Search in Google Scholar

[22] Kalina, J. (2019). Common multivariate estimators of location and scatter capture the symmetry of the underlying distribution. Communications in Statistics—Simulation and Computation. In press.Search in Google Scholar

[23] Víšek, J.Á. (2010). Robust error-term-scale estimate. IMS Collections, 7, 254–267.10.1214/10-IMSCOLL725Search in Google Scholar

[24] Rousseeuw, P.J. & Van Driessen, K. (2006). Computing LTS regression for large data sets. Data Mining and Knowledge Discovery, 12, 29–45.10.1007/s10618-005-0024-4Search in Google Scholar

[25] Kalina, J. & Neoral, A. (2019). A robustified metalearning procedure for regression estimators. In Conference Proceedings, The 13th International Days of Statistics and Economics MSED 2019. Slaný: Melandrium, 617–726.10.18267/pr.2019.los.186.61Search in Google Scholar

[26] R Core Team (2020). R: A language and environment for statistical computing. R Foundation for Statistical Computing, Vienna, Austria. URL http://www.R-project.org/.Search in Google Scholar

Recommended articles from Trend MD

Plan your remote conference with Sciendo