A robust conditional maximum likelihood estimator for generalized linear models with a dispersion parameter

Highly robust and efficient estimators for generalized linear models with a dispersion parameter are proposed. The estimators are based on three steps. In the first step, the maximum rank correlation estimator is used to consistently estimate the slopes up to a scale factor. The scale factor, the in...

Descripción completa

Guardado en:
Detalles Bibliográficos
Autor principal: Marazzi, A.
Otros Autores: Valdora, M., Yohai, V., Amiguet, M.
Formato: Capítulo de libro
Lenguaje:Inglés
Publicado: Springer New York LLC 2019
Acceso en línea:Registro en Scopus
DOI
Handle
Registro en la Biblioteca Digital
Aporte de:Registro referencial: Solicitar el recurso aquí
LEADER 09097caa a22008297a 4500
001 PAPER-25626
003 AR-BaUEN
005 20230518205742.0
008 190410s2019 xx ||||fo|||| 00| 0 eng|d
024 7 |2 scopus  |a 2-s2.0-85058084037 
040 |a Scopus  |b spa  |c AR-BaUEN  |d AR-BaUEN 
100 1 |a Marazzi, A. 
245 1 2 |a A robust conditional maximum likelihood estimator for generalized linear models with a dispersion parameter 
260 |b Springer New York LLC  |c 2019 
270 1 0 |m Marazzi, A.; Institute of Social and Preventive MedicineSwitzerland; email: alfio.marazzi@chuv.ch 
506 |2 openaire  |e Política editorial 
504 |a Abrevaya, J., Computation of the maximum rank correlation estimator (1999) Econ Lett, 62, pp. 279-285 
504 |a Aeberhard, W.H., Cantoni, E., Heritier, S., Robust inference in the negative binomial regression model with an application to falls data (2014) Biometrics, 70, pp. 920-931 
504 |a Agostinelli, C., Marazzi, A., (2018) Robustnegbin: Robust Estimates for the Negative Binomial Regression Model, , R package, Preliminary version 
504 |a Alfons, A., (2015), ccaPP: (Robust) canonical correlation analysis via projection pursuit. R package version 0.3.1; Alfons, A., Croux, C., Filzmoser, P., Robust maximum association estimators (2017) J Am Stat Assoc, 112 (517), pp. 436-445 
504 |a Amiguet, M., (2011) Adaptively Weighted Maximum Likelihood Estimation of Discrete Distributions, , Ph.D. thesis, Université de Lausanne, Switzerland 
504 |a Austin, P.C., Rothwell, D.M., Tu, J.V., A comparison of statistical modeling strategies for analyzing length of stay after CABG surgery (2002) Health Serv Outcomes Res Methodol, 3, pp. 107-133 
504 |a Cadigan, N.G., Chen, J., Properties of robust M-estimators for Poisson and negative binomial data (2001) J Stat Comput Simul, 70, pp. 273-288 
504 |a Cantoni, E., Ronchetti, E., Robust inference for generalized linear models (2001) J Am Stat Assoc, 96 (455), pp. 1022-1030 
504 |a Cantoni, E., Zedini, A., (2009) A robust version of the hurdle model, , Cahiers du département d’économétrie No 2009.07, Faculté des sciences économiques et sociales, Université de Genève 
504 |a Carter, E.M., Potts, H.W.W., Predicting length of stay from an electronic patient record system: a primary total knee replacement example (2014) BMC Med Inform Decis Mak, 14, p. 26 
504 |a Cuesta-Albertos, J.A., Matrán, C., Mayo-Iscar, A., Trimming and likelihood: robust location and dispersion estimate in the elliptical model (2008) Ann Stat, 36 (5), pp. 2284-2318 
504 |a Davison, A.C., Snell, E.J., Residuals and diagnostics (1991) Statistical theory and modelling: in honour of Sir David Cox, pp. 83-106. , Hinkley DV, Reid N, Snell EJ, (eds), Chapman and Hall, Boca Raton 
504 |a Dunn, P.K., Smyth, G.K., Randomized quantile residuals (1996) J Comput Graph Stat, 5 (3), pp. 236-244 
504 |a Gervini, D., Yohai, V.J., A class of robust and fully efficient regression estimators (2002) Ann Stat, 30 (2), pp. 583-616 
504 |a Ghosh, A., Basu, A., Robust estimation for independent non-homogeneous observations using density power divergence with applications to linear regression (2013) Electron J Stat, 7, pp. 2420-2456 
504 |a Ghosh, A., Basu, A., Robust estimation in generalized linear models: the density power divergence approach (2016) TEST, 25, pp. 269-290 
504 |a Hampel, F.R., Ronchetti, E.M., Rousseeuw, P.J., Stahel, W.A., (1986) Robust statistics: the approach based on influence functions, , Wiley, New York 
504 |a Han, A.K., Non-parametric analysis of a generalized regression model: the maximum rank correlation estimator (1987) J Econ, 35 (23), pp. 303-316 
504 |a Han, A.K., A non-parametric analysis of transformations (1987) J Econ, 35 (2-3), pp. 191-209 
504 |a Heritier, S., Cantoni, E., Copt, S., Victoria-Feser, M.P., (2009) Robust methods in biostatistics, , Wiley, Chichester 
504 |a Hilbe, J.M., (2008) Negative binomial regression, , Cambridge University Press, Cambridge 
504 |a Huber, P.J., (1980) Robust statistics, , Wiley, New York 
504 |a Künsch, H.R., Stefanski, L.A., Carroll, R.J., Conditionally unbiased bounded-influence estimation in general regression models, with applications to generalized linear models (1989) J Am Stat Assoc, 84 (406), pp. 460-466 
504 |a Locatelli, I., Marazzi, A., Yohai, V.J., Robust accelerated failure time regression (2010) Comput Stat Data Anal, 55 (1), pp. 874-887 
504 |a Marazzi, A., Yohai, V.J., Adaptively truncated maximum likelihood regression with asymmetric errors (2004) J Stat Plan Inference, 122 (1-2), pp. 271-291 
504 |a Marazzi, A., Yohai, V.J., Optimal robust estimates based on the Hellinger distance (2010) Adv Data Anal Classif, 4 (2), pp. 169-179 
504 |a Marazzi, A., Paccaud, F., Ruffieux, C., Beguin, C., Fitting the distribution of length of stay by parametric models (1998) Med Care, 36 (6), pp. 915-927 
504 |a Maronna, R.A., Martin, R.D., Yohai, V.J., (2006) Robust statistics theory and methods, , Wiley, New York 
504 |a Min, Y., Agresti, A., Modeling nonnegative data with clumping at zero: a survey (2002) J Iran Stat Soc, 1 (1-2), pp. 7-33 
504 |a Nelder, J.A., Wedderburn, R.W.M., Generalized linear models (1972) J R Stat Soc Ser A, 135 (3), pp. 370-384 
504 |a Rousseeuw, P.J., Multivariate estimation with high breakdwon point (1985) Mathematical statistics and applications, pp. 283-297. , Grossman W, Pflug G, Vincze I, Wertz W, (eds), Reidel Publishing, Dordrecht 
504 |a Sherman, R.P., The limiting distribution of the maximum rank correlation estimator (1993) Econometrica, 61 (1), pp. 123-137 
504 |a Valdora, M., Yohai, V.J., Robust estimation in generalized linear models (2014) J Stat Plan Inference, 146, pp. 31-48 
504 |a Yohai, V.J., High breakdown-point and high efficiency robust estimates for regression (1987) Ann Stat, 15 (2), pp. 642-656 
520 3 |a Highly robust and efficient estimators for generalized linear models with a dispersion parameter are proposed. The estimators are based on three steps. In the first step, the maximum rank correlation estimator is used to consistently estimate the slopes up to a scale factor. The scale factor, the intercept, and the dispersion parameter are robustly estimated using a simple regression model. Then, randomized quantile residuals based on the initial estimators are used to define a region S such that observations out of S are considered as outliers. Finally, a conditional maximum likelihood (CML) estimator given the observations in S is computed. We show that, under the model, S tends to the whole space for increasing sample size. Therefore, the CML estimator tends to the unconditional maximum likelihood estimator and this implies that this estimator is asymptotically fully efficient. Moreover, the CML estimator maintains the high degree of robustness of the initial one. The negative binomial regression case is studied in detail. © 2018, Sociedad de Estadística e Investigación Operativa.  |l eng 
536 |a Detalles de la financiación: Victor Yohai was partially supported by grants pict 2014-0351 from anpcyt and 20020130100279BA from the Universidad de Buenos Aires at Buenos Aires, Argentina. Marina Valdora was partially supported by grant 20020130100279Ba from the Universidad de Buenos Aires at Buenos Aires, Argentina. We also thank two anonymous referees for their valuable comments that helped to improve the presentation of the paper. 
593 |a Institute of Social and Preventive Medicine, Lausanne, Switzerland 
593 |a Nice Computing, Le Mont-sur-Lausanne, Switzerland 
593 |a Departamento de matematicas and Instituto de cálculo, Facultad de ciencias exactas y naturales, Universidad de Buenos Aires, Buenos Aires, Argentina 
593 |a CONICET, Buenos Aires, Argentina 
690 1 0 |a CONDITIONAL MAXIMUM LIKELIHOOD 
690 1 0 |a GENERALIZED LINEAR MODEL 
690 1 0 |a NEGATIVE BINOMIAL REGRESSION 
690 1 0 |a OVERDISPERSION 
690 1 0 |a ROBUST REGRESSION 
700 1 |a Valdora, M. 
700 1 |a Yohai, V. 
700 1 |a Amiguet, M. 
773 0 |d Springer New York LLC, 2019  |g v. 28  |h pp. 223-241  |k n. 1  |p Test  |x 11330686  |t Test 
856 4 1 |u https://www.scopus.com/inward/record.uri?eid=2-s2.0-85058084037&doi=10.1007%2fs11749-018-0624-0&partnerID=40&md5=9aac02a917ce3e188a4a981fda524c60  |y Registro en Scopus 
856 4 0 |u https://doi.org/10.1007/s11749-018-0624-0  |y DOI 
856 4 0 |u https://hdl.handle.net/20.500.12110/paper_11330686_v28_n1_p223_Marazzi  |y Handle 
856 4 0 |u https://bibliotecadigital.exactas.uba.ar/collection/paper/document/paper_11330686_v28_n1_p223_Marazzi  |y Registro en la Biblioteca Digital 
961 |a paper_11330686_v28_n1_p223_Marazzi  |b paper  |c PE 
962 |a info:eu-repo/semantics/article  |a info:ar-repo/semantics/artículo  |b info:eu-repo/semantics/publishedVersion 
999 |c 86579