Robust mixture multivariate linear regression by multivariate Laplace distribution. (English) Zbl 1391.62050
Summary: Assuming that the error terms follow a multivariate Laplace distribution, we propose a robust estimation procedure for mixture of multivariate linear regression models in this paper. Using the fact that the multivariate Laplace distribution is a scale mixture of the multivariate standard normal distribution, an efficient EM algorithm is designed to implement the proposed robust estimation procedure. The performance of the proposed algorithm is thoroughly evaluated by some simulation and comparison studies.
MSC:
| 62F35 | Robustness and adaptive procedures (parametric inference) |
| 62F10 | Point estimation |
| 62J05 | Linear regression; mixed models |
| 62H12 | Estimation in multivariate analysis |
Keywords:
finite mixtures; multivariate linear regression; robust estimation; multivariate Laplace distribution; EM algorithmReferences:
| [1] | Anderson, D. N., A multivariate linnik distribution, Stat. Probab. Lett., 14, 4, 333-336 (1992) · Zbl 0754.60022 |
| [2] | Bai, X.; Yao, W.; Boyer, J. E., Robust fitting of mixture regression models, Comput. Stat. Data Anal., 56, 7, 2347-2359 (2012) · Zbl 1252.62011 |
| [3] | Bashir, S.; Carter, E., Robust mixture of linear regression models, Commun. Stat. - Theory Methods, 41, 18, 3371-3388 (2012) · Zbl 1296.62111 |
| [4] | Böhning, D., Computer-assisted Analysis of Mixtures and Applications: Meta-analysis, Disease Mapping and Others, Vol. 81 (2000), CRC press · Zbl 0951.62088 |
| [5] | Dielman, T., Least absolute value estimation in regression models: an annotated bibliography, Comm. Statis. Theory Methods, 4, 513-541 (1984) · Zbl 0551.62043 |
| [6] | Dielman, T., Least absolute value regression: recent contributions, J. Statis. Comput. Simul., 75, 263-286 (2005) · Zbl 1059.62070 |
| [7] | Donoho, D., Breakdown properties of multivariate location estimators, Qualifying Paper, Harvard University, Boston (1982) |
| [8] | Eltoft, T.; Kim, T.; Lee, T.-W., On the multivariate laplace distribution, IEEE Signal Process. Lett., 13, 5, 300-303 (2006) |
| [9] | Ernst, M. D., A multivariate generalized laplace distribution, Comput. Statist., 13, 2, 227-232 (1998) · Zbl 0922.62043 |
| [10] | Fang, K.-T.; Kotz, S.; Ng, K. W., Symmetric Multivariate and Related Distributions (1990), Chapman and Hall · Zbl 0699.62048 |
| [11] | Farcomeni, A.; Greco, L., Robust Methods for Data Reduction (2015), CRC Press, Taylor Francis Group, LLC · Zbl 1311.62006 |
| [12] | Fernandez, C.; Osiewalski, J.; Steel, M. F., Modeling and inference with \(\upsilon \)-spherical distributions, J. Amer. Statist. Assoc., 90, 432, 1331-1340 (1995) · Zbl 0868.62045 |
| [13] | Huang, M.; Li, R.; Wang, S., Nonparametric mixture of regression models, J. Amer. Statist. Assoc., 108, 503, 929-941 (2013) · Zbl 06224977 |
| [14] | Jiang, W.; Tanner, M. A., Hierarchical mixtures-of-experts for exponential family regression models: approximation and maximum likelihood estimation, Ann. Statist., 987-1011 (1999) · Zbl 0957.62032 |
| [15] | Kotz, S.; Kozubowski, T.; Podgorski, K., The Laplace Distribution and Generalizations: A Revisit with Applications to Communications, Economics, Engineering, and Finance (2012), Springer Science & Business Media |
| [16] | Li, Y.; Arce, G., A maximum likelihood approach to least absolute deviation regression, J. Appl. Signal Process., 12, 1762-1769 (2004) |
| [17] | Lin, T.-I., Robust mixture modeling using multivariate skew t distributions, Stat. Comput., 20, 3, 343-356 (2010) |
| [18] | McLachlan, G.; Peel, D., Finite Mixture Models (2004), John Wiley & Sons |
| [19] | Newcomb, S., A generalized theory of the combination of observations so as to obtain the best result, Am. J. Math., 343-366 (1886) · JFM 18.0183.01 |
| [20] | Neykov, N.; Filzmoser, P.; Dimova, R.; Neytchev, P., Robust fitting of mixtures using the trimmed likelihood estimator, Comput. Stat. Data Anal., 52, 1, 299-308 (2007) · Zbl 1328.62033 |
| [21] | Peel, D.; McLachlan, G., Robust mixture modelling using the t-distribution, Stat. Comput., 10, 339-348 (2000) |
| [22] | Portilla, J.; Strela, V.; Wainwright, M. J.; Simoncelli, E. P., Image denoising using scale mixtures of gaussians in the wavelet domain, IEEE Trans. Image Process., 12, 11, 1338-1351 (2003) · Zbl 1279.94028 |
| [23] | Rousseeuw, P.; Van Aelst, S.; Van Driessen, K.; Agullø, J., Robust multivariate regression, Technometrics, 46, 3, 293-305 (2004) |
| [24] | Rousseeuw, P. J., V. D.K., A fast algorithm for the minimum covariance determinant estimator, Technometrics, 41, 212-223 (1999) |
| [25] | Samko, S. G.; Kilbas, A. A.; Marichev, O. I., Fractional integrals and derivatives. 1993, Gordon & Breach Science Publishers (1987) · Zbl 0617.26004 |
| [26] | Song, W.; Yao, W.; Xing, Y., Robust mixture regression model fitting by laplace distribution, Comput. Stat. Data Anal., 71, 128-137 (2014) · Zbl 1471.62189 |
| [27] | Spanier, J.; Oldham, K. B., An Atlas of Functions (1987), Taylor & Francis/Hemisphere · Zbl 0618.65007 |
| [28] | Stahel, W. A., Robuste Schätzungen: Infinitesimale Optimalität und Schätzungen von Kovarianzmatrizen (1981), Ph.D. thesis, ETH Zürich · Zbl 0531.62036 |
| [29] | Ulrich, G.; Chen, C., A bivariate double exponential distribution and its generalization, (ASA Proceedings on Statistical Computing (1987)), 127-129 |
| [30] | Wedel, M.; Kamakura, W. A., Market Segmentation: Conceptual and Methodological Foundations (2012), Springer Science & Business Media |
| [31] | Xian Wang, H.; bing Zhang, Q.; Luo, B.; Wei, S., Robust mixture modelling using multivariate t-distribution with missing information, Pattern Recognit. Lett., 25, 6, 701-710 (2004) |
| [32] | Yao, W.; Wei, Y.; Yu, C., Robust mixture regression using the t-distribution, Comput. Stat. Data Anal., 71, 116-127 (2014) · Zbl 1471.62227 |
This reference list is based on information provided by the publisher or from digital mathematics libraries. Its items are heuristically matched to zbMATH identifiers and may contain data conversion errors. In some cases that data have been complemented/enhanced by data from zbMATH Open. This attempts to reflect the references listed in the original paper as accurately as possible without claiming completeness or a perfect matching.
