Adaptive estimation of the conditional intensity of marker-dependent counting processes
Annales de l'I.H.P. Probabilités et statistiques, Tome 47 (2011) no. 4, pp. 1171-1196.

Dans ce travail, nous proposons un estimateur original de l'intensité conditionnelle d'un processus de comptage marqué, c'est-à-dire d'un processus de comptage dépendant de covariables. Nous utilisons une méthode de sélection de modèle et nous obtenons pour notre estimateur, une borne non asymptotique du risque quadratique sur un compact. Nous vérifions ensuite que l'estimateur atteint automatiquement une vitesse de convergence sur des classes fonctionnelles de régularité anisotropique fixée mais inconnue. Enfin, nous démontrons une borne inférieure qui garantit l'optimalité de la vitesse obtenue. Une brève illustration de la façon dont fonctionne l'estimateur dans le contexte de l'estimation du taux de risque instantané conditionnel est fournie pour conclure.

We propose in this work an original estimator of the conditional intensity of a marker-dependent counting process, that is, a counting process with covariates. We use model selection methods and provide a nonasymptotic bound for the risk of our estimator on a compact set. We show that our estimator reaches automatically a convergence rate over a functional class with a given (unknown) anisotropic regularity. Then, we prove a lower bound which establishes that this rate is optimal. Lastly, we provide a short illustration of the way the estimator works in the context of conditional hazard estimation.

DOI : https://doi.org/10.1214/10-AIHP386
Classification : 62N02,  62G05
Mots clés : marker-dependent counting process, conditional intensity, model selection, adaptive estimation, minimax and nonparametric methods, censored data, conditional hazard function
@article{AIHPB_2011__47_4_1171_0,
     author = {Comte, F. and Ga{\"\i}ffas, S. and Guilloux, A.},
     title = {Adaptive estimation of the conditional intensity of marker-dependent counting processes},
     journal = {Annales de l'I.H.P. Probabilit\'es et statistiques},
     pages = {1171--1196},
     publisher = {Gauthier-Villars},
     volume = {47},
     number = {4},
     year = {2011},
     doi = {10.1214/10-AIHP386},
     zbl = {1271.62222},
     language = {en},
     url = {http://www.numdam.org/articles/10.1214/10-AIHP386/}
}
Comte, F.; Gaïffas, S.; Guilloux, A. Adaptive estimation of the conditional intensity of marker-dependent counting processes. Annales de l'I.H.P. Probabilités et statistiques, Tome 47 (2011) no. 4, pp. 1171-1196. doi : 10.1214/10-AIHP386. http://www.numdam.org/articles/10.1214/10-AIHP386/

[1] P. K. Andersen, O., Borgan, R. D. Gill and N. Keiding. Statistical Models Based on Counting Processes. Springer, New York, 1993. | MR 1198884 | Zbl 0824.60003

[2] Y. Baraud. A Bernstein-type inequality for suprema of random processes with an application to statistics. Bernoulli (2010). To appear. | MR 2759169

[3] Y. Baraud and L. Birgé. Estimating the intensity of a random measure by histogram type estimators. Probab. Theory Related Fields 149 (2009) 239-284. | MR 2449129 | Zbl 1149.62019

[4] A. Barron, L. Birgé and P. Massart. Risk bounds for model selection via penalization. Probab. Theory Related Fields 113 (1999) 301-413. | MR 1679028 | Zbl 0946.62036

[5] J. Beran. Nonparametric regression with randomly censored survival data. Technical report, Dept. Statist., Univ. California, Berkeley, 1981.

[6] L. Birgé and P. Massart. Minimum contrast estimators on sieves: Exponential bounds and rates of convergence. Bernoulli 4 (1998) 329-375. | MR 1653272 | Zbl 0954.62033

[7] E. Brunel, F. Comte and C. Lacour. Adaptive estimation of the conditional density in presence of censoring. Sankhyā A 69 (2007) 734-763. | MR 2521231 | Zbl 1193.62055

[8] G. Castellan and F. Letué. Estimation of the Cox regression function via model selection. Chapter of the PhD thesis of F. Letué, Univ. Paris XI-Orsay, 2000.

[9] A. Cohen, I. Daubechies and P. B. Vial. Wavelets on the interval and fast wavelet transforms. Appl. Comput. Harmon. Anal. 1 (1993) 54-81. | MR 1256527 | Zbl 0795.42018

[10] F. Comte. Adaptive estimation of the spectrum of a stationary Gaussian sequence. Bernoulli 7 (2001) 267-298. | MR 1828506 | Zbl 0981.62075

[11] F. Comte, S. Gaïffas and A. Guilloux. Adaptive estimation of the conditional intensity of marker-dependent counting processes. Preprint MAP5 2008-16, revised 2010. Available at http://hal.archives-ouvertes.fr/hal-00333356/fr/.

[12] D. R. Cox. Regression models and life-tables (with discussion). J. R. Stat. Soc. Ser. B Stat. Methodol. 34 (1972) 187-220. | MR 341758 | Zbl 0243.62041

[13] D. M. Dabrowska. Nonparametric regression with censored survival time data. Scand. J. Statist. 14 (1987) 181-197. | MR 932943 | Zbl 0641.62024

[14] D. M. Dabrowska. Uniform consistency of the kernel conditional Kaplan-Meier estimate. Ann. Statist. 17 (1989) 1157-1167. | MR 1015143 | Zbl 0687.62035

[15] I. Daubechies. Orthonormal bases of compactly supported wavelets. Comm. Pure Appl. Math. 41 (1988) 909-996. | MR 951745 | Zbl 0644.42026

[16] M. Delecroix, O. Lopez and V. Patilea. Nonlinear censored regression using synthetic data. Scand. J. Statist. 35 (2008) 248-265. | MR 2418739 | Zbl 1164.62024

[17] G. Grégoire. Least squares cross-validation for counting processes intensities. Scand. J. Statist. 20 (1993) 343-360. | MR 1276698 | Zbl 0795.62031

[18] C. Heuchenne and I. Van Keilegom. Location estimation in nonparametric regression with censored data. J. Multivariate Anal. 98 (2007) 1558-1582. | MR 2370107 | Zbl 1122.62024

[19] R. Hochmuth. Wavelet characterizations for anisotropic Besov spaces. Appl. Comput. Harmon. Anal. 12 (2002) 179-208. | MR 1884234 | Zbl 1003.42024

[20] J. Huang. Efficient estimation of the partly linear additive Cox model. Ann. Statist. 27 (1999) 1536-1563. | MR 1742499 | Zbl 0977.62035

[21] M. Jacobsen. Statistical Analysis of Counting Processes. Lecture Note in Statistics 12. Springer, New York, 1982. | MR 676128 | Zbl 0518.60065

[22] A. F. Karr. Point Processes and Their Statistical Inference. Marcel Dekker, New York, 1986. | MR 851982 | Zbl 0733.62088

[23] C. Lacour. Adaptive estimation of the transition density of a Markov chain. Ann. Inst. H. Poincaré Probab. Statist. 43 (2007) 571-597. | Numdam | MR 2347097 | Zbl 1125.62087

[24] C. Lacour. Estimation non paramétrique adaptative pour les chaînes de Markov et les chaînes de Markov cachées. PhD thesis, 2007. Available at http://www.math.u-psud.fr/~lacour/etudes/.

[25] M. Leblanc and J. Crowley. Adaptive regression splines in the Cox model. Biometrics 55 (1999) 204-213. | Zbl 1059.62668

[26] G. Li and H. Doss. An approach to nonparametric regression for life history data using local linear fitting. Ann. Statist. 23 (1995) 787-823. | MR 1345201 | Zbl 0852.62037

[27] O. B. Linton, J. P. Nielsen and S. Van De Geer. Estimating the multiplicative and additive hazard functions by kernel methods. Ann. Statist. 31 (2003) 464-492. | MR 1983538 | Zbl 1040.62089

[28] R. S. Liptser and A. N. Shiryayev. Theory of Martingales. Mathematics and its Applications (Soviet Series) 49. Kluwer Academic, Dordrecht, 1989. | MR 1022664 | Zbl 0728.60048

[29] P. Massart. Concentration Inequalities and Model Selection. Lecture Notes in Mathematics 1896. Springer, Berlin, 2007. | MR 2319879 | Zbl 1170.60006

[30] I. W. Mckeague and K. J. Utikal. Inference for a nonlinear counting process regression model. Ann. Statist. 18 (1990) 1172-1187. | MR 1062704 | Zbl 0721.62087

[31] Y. Meyer. Ondelettes sur l'intervalle. Rev. Mat. Iberoamericana 7 (1991) 115-133. | MR 1133374 | Zbl 0753.42015

[32] S. M. Nikol'Skii. Approximation of Functions of Several Variables and Imbedding Theorems. Springer, New York, 1975. | Zbl 0185.37901

[33] H. Ramlau-Hansen. Smoothing counting process intensities by means of kernel functions. Ann. Statist. 11 (1983) 453-466. | MR 696058 | Zbl 0514.62050

[34] P. Reynaud-Bouret. Adaptive estimation of the intensity of nonhomogeneous Poisson processes via concentration inequalities. Probab. Theory Related Fields 126 (2003) 103-153. | MR 1981635 | Zbl 1019.62079

[35] P. Reynaud-Bouret. Penalized projection estimators of the Aalen multiplicative intensity. Bernoulli 12 (2006) 633-661. | MR 2248231 | Zbl 1125.62027

[36] C. J. Stone. Optimal rates of convergence for nonparametric estimators. Ann. Statist. 8 (1980) 1348-1360. | MR 594650 | Zbl 0451.62033

[37] W. Stute. Conditional empirical processes. Ann. Statist. 14 (1986) 638-647. | MR 840519 | Zbl 0594.62038

[38] W. Stute. Distributional convergence under random censorship when covariables are present. Scand. J. Statist. 23 (1996) 461-471. | MR 1439707 | Zbl 0903.62045

[39] M. Talagrand. The Generic Chaining. Springer, Berlin, 2005. | MR 2133757 | Zbl 1075.60001

[40] H. Triebel. Theory of Function Spaces. III. Monographs in Mathematics 100. Birkhäuser, Basel, 2006. | MR 2250142 | Zbl 1104.46001

[41] A. Tsybakov. Introduction à l'estimation non-paramétrique. Springer, Berlin, 2004. | MR 2013911 | Zbl 1029.62034

[42] S. Van De Geer. Exponential inequalities for martingales, with application to maximum likelihood estimation for counting processes. Ann. Statist. 23 (1995) 1779-1801. | MR 1370307 | Zbl 0852.60019