Abstract
Usual fitting methods for the nested error linear regression model are known to be very sensitive to the effect of even a single outlier. Robust approaches for the unbalanced nested error model with proved robustness and efficiency properties, such as M-estimators, are typically obtained through iterative algorithms. These algorithms are often computationally intensive and require robust estimates of the same parameters to start the algorithms, but so far no robust starting values have been proposed for this model. This paper proposes computationally fast robust estimators for the variance components under an unbalanced nested error model, based on a simple robustification of the fitting-of-constants method or Henderson method III. These estimators can be used as starting values for other iterative methods. Our simulations show that they are highly robust to various types of contamination of different magnitude.
Similar content being viewed by others
References
Chambers, R., Tzavidis, N.: M-quantile models for small area estimation. Biometrika. 93, 255–268 (2006)
Copt, S., Heritier, S.: Robust alternatives to the \(F\)-test in mixed linear models based on \(MM\)-estimates. Biometrics. 63, 1045–1052 (2007)
Copt, S., Victoria-Feser, M.P.: High-breakdown inference for mixed linear models. J. Am. Statist. Assoc. 101, 292–300 (2006)
Gervini, D., Yohai, V.J.: Robust estimation of variance components. Can. J. Stat. 26, 419–430 (1998)
Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A.: Robust Statistics. The Approach Based on Influence Functions. Wiley, New York (1986)
Henderson, C.R.: Estimation of variance and covariance components. Biometrics 9, 226–252 (1953)
Henderson, C.R.: Best linear unbiased estimation and prediction under a selection model. Biometrics. 31, 423–447 (1975)
Hocking, R.R.: A new approach to variance component estimation with diagnostic implications. Commun. Stat.- Theor.M. 19, 4591–4617 (1990)
Hocking, R.R., Green, J.W., Bremer, R.H.: Variance component estimation with model-based diagnostics. Technometrics. 31, 227–239 (1989)
Huber, P.J.: Robust statistics. Wiley, Hoboken (1981)
Huggins, R.M.: A robust approach to the analysis of repeated measures. Biometrics 49, 715–720 (1993)
Huggins, R.M., Staudte, R.G.: Cell lineage analysis: variance component models for dependent cell populations. J. Am. Statist. Assoc. 89, 19–29 (1994)
Maronna, R.A., Yohai, V.J.: Robust regression with both continuous and categorical predictors. J. Stat. Plan. Infer. 89, 197–214 (2000)
Mehrotra, D.V.: Non-iterative robust estimators of variance components in within-subject designs. Stat. Med. 16, 1465–1479 (1997)
Prasad, N.G.N., Rao, J.N.K.: The estimation of the mean squared error of small-area estimators. J. Am. Statist. Assoc. 85, 163–171 (1990)
Rao, J.N.K., Molina, I.: Small Area Estimation, 2nd edn. Wiley, Hoboken (2015)
Richardson, A.M.: Bounded influence estimation in the mixed linear model. J. Am. Statist. Assoc. 92, 154–161 (1997)
Richardson, A.M., Welsh, A.H.: Robust restricted maximum likelihood in mixed linear models. Biometrics. 51, 1429–1439 (1997)
Rocke, D.M.: Robust statistical analysis of interlaboratory studies. Biometrika. 70, 421–431 (1983)
Rocke, D.M.: Robustness and balance in the mixed model. Biometrics. 47, 303–309 (1991)
Rousseeuw, P., Croux, C., Todorov, V., Ruckstuhl, A., Salibian-Barrera, M., Verbeke, T., Koller, M. and Maechler, M.: Robustbase: basic robust statistics. R package version 0.92-5. (2015). http://CRAN.R-project.org/package=robustbase
Sinha, S.K., Rao, J.N.K.: Robust small area estimation. Can. J. Stat. 37, 381–399 (2009)
Stahel, W.A., Welsh, A.: Approaches to robust estimation in the simplest variance components model. J. Stat. Plan. Infer. 57, 297–319 (1997)
Vangeneugden, T., Laenen, A., Geys, H., Renard, D., Molenberghs, G.: Applying linear mixed models to estimate reliability in clinical trial data with repeated measurements. Control. Clin. Trials. 25, 13–30 (2004)
Wang, J., Zamar, R., Marazzi, A., Yohai, V., Salibian-Barrera, M., Maronna, R., Zivot, E., Rocke, D., Martin, D., Maechler, M., and Konis, K.: Robust, a package of robust methods, R package version 0.4-16, (2013). http://CRAN.R-project.org/package=robust
Wellenius, G.A., Yeh, G.Y., Coull, B.A., Suh, H.H., Phillips, R.S., Mittlemann, M.A.: Effects of ambient air pollution on functional status in patients with chronic congestive heart failure: repeated-measures study. Environ. Health-Glob. 6, 1–7 (2007)
Wellmann, J.: Robuste Statistische Verfahren un Ausreisseridentifikation beim Modell del Einfachklassification mit zufälligen Effekten. Ph.D. Thesis, Department of Statistics, University of Dortmund (1994)
Wellmann, J.: Robustness of an S-estimator in the one-way random effects model. Biometrical J. 42, 215–221 (2000)
Wellmann, J., Gather, U.: Identification of outliers in one-way random effects model. Stat. Pap. 44, 335–348 (2003)
Welsh, A.H., Richardson, A.M.: Approaches to the robust estimation of mixed models. In: Maddala, G.S., Rao, C.R. (eds.) Handbook of Statistics, pp. 343–384. Elsevier Science, Amsterdam (1997)
Yohai, V., Stahel, W.A., Zamar, R.H.: A procedure for robust estimation and inference in linear regression. In: Stahel, W.A., Weisberg, S.W. (eds.) Directions in Robust Statistics and Diagnostics. Springer, Berlin (1991)
Acknowledgments
Supported by the Spanish grants MTM2015-69638-R, MTM2012-37077-C02-01 and SEJ2007-64500, and by the European project num. 217565-FP7-SSH-2007-1
Author information
Authors and Affiliations
Corresponding author
Electronic supplementary material
Below is the link to the electronic supplementary material.
Rights and permissions
About this article
Cite this article
Pérez, B., Molina, I., Thieler, A. et al. Fast and robust estimators of variance components in the nested error model. Stat Comput 27, 1655–1675 (2017). https://doi.org/10.1007/s11222-016-9710-x
Received:
Accepted:
Published:
Issue Date:
DOI: https://doi.org/10.1007/s11222-016-9710-x