Estimation de la fonction de répartition : revue bibliographique

Servien, Rémi

Journal de la société française de statistique, Tome 150 (2009) no. 2, pp. 84-104.

L’estimation de la fonction de répartition d’une variable aléatoire est un volet important de l’estimation non paramétrique. De nombreuses méthodes ont été proposées et étudiées afin de modifier efficacement l’outil brut qu’est la fonction de répartition empirique. Dans cet article, nous effectuons un point bibliographique sur les différentes méthodes envisagées dans le cas de variables aléatoires réelles.

The estimation of the distribution function of a real random variable is an important topic in non parametric estimation. A number of methods have been proposed and studied to improve the efficiency of the raw empirical distribution function in a broad variety of context. The present paper aims at giving an overview of these methods.

[1] Abdous, B.; Berlinet, A.; Hengartner, N. A general theory for kernel estimation of smooth functionals of the distribution function and their derivatives, Revue Roumaine de Mathématiques Pures et Appliquées, Volume 48 (2003), pp. 217-232 | MR | Zbl

[2] Aggarwal, O.P. Some minimax invariant procedures for estimating a cumulative distribution function, The Annals of Mathematical Statistics, Volume 26 (1955), pp. 450-462 | MR | Zbl

[3] Akaike, H. An approximation to the density function, Annals of the Institute of Statistical Mathematics, Volume 6 (1954), pp. 127-132 | MR | Zbl

[4] Azzalini, A. A note on the estimation of a distribution function and quantiles by a kernel method, Biometrika, Volume 68 (1981), pp. 326-328 | MR

[5] Berlinet, A.; Biau, G. Estimation de densité et prise de décision, Décision et Reconnaissance de Formes en Signal (Lengellé, R., ed.), Hermes, Paris, 2002

[6] Bleuez, J.; Bosq, D. Conditions nécessaires et suffisantes de convergence pour une classe d’estimateurs de la densité par la méthode des fonctions orthogonales, Comptes rendus de l’Académie des Sciences de Paris Série A, Volume 282 (1976), pp. 1023-1026 | MR | Zbl

[7] Bleuez, J.; Bosq, D. Conditions nécessaires et suffisantes de convergence pour une classe d’estimateurs de la densité, Comptes rendus de l’Académie des Sciences de Paris Série A, Volume 282 (1976), pp. 63-66 | MR | Zbl

[8] Barlow, R.; Bartholomew, D.; Brewner, J.; Brunk, H. Statistical inferences under order restrictions, Wiley, New-York, 1972 | Zbl

[9] Barnsley, M.F.; Demko, S. Iterated function systems and the global construction of fractals, Proceedings of the Royal Society of London. Series A, Mathematical and Physical Sciences, Volume 399 (1985), pp. 243-275 | MR | Zbl

[10] Beran, R. Estimating a distribution function, The Annals of Statistics, Volume 5 (1977), pp. 400-404 | MR | Zbl

[11] Berlinet, A. Convergence des estimateurs splines de la densité, Publications de l’Institut de Statistique de l’Université de Paris, Volume 26 (1981), pp. 1-16 | Zbl

[12] Berlinet, A. Reproducing kernels and finite order kernels, Nonparametric Functional Estimation and Related Topics (Roussas, G.G., ed.), Klüwer Academic Publishers, Dordrecht, 1991 | MR | Zbl

[13] Billingsley, P. Convergence of Probability Measures, Wiley, New-York, 1968 | MR

[14] Bosq, D.; Lecoutre, J.-P. Théorie de l’Estimation Fonctionnelle, Economica, 1987

[15] Brown, L.D. Admissibility in discrete and continuous invariant non-parametric estimation problems, and in their multinomial analogs, The Annals of Statistics, Volume 16 (1988), pp. 1567-1593 | MR | Zbl

[16] Bernardo, J.M.; Smith, A.F.M. Bayesian Theory, Wiley, New-York, 1994 | MR

[17] Berlinet, A.; Thomas-Agnan, C. Reproducing Kernel in Hilbert Spaces in Probability and Statistics, Klüwer, Boston, 2004 | MR | Zbl

[18] Besse, P.; Thomas-Agnan, C. Le lissage par fonctions splines en statistique : revue bibliographique, Statistique et Analyse des données, Volume 14 (1989), pp. 55-83

[19] Burges, C.J.C. A tutorial on support vector machines for pattern recognition, Data mining and knowledge discovery, Volume 2 (1998), pp. 1-47

[20] Collomb, G.; Hassani, S.; Sarda, P.; Vieu, P. Estimation non paramétrique de la fonction de hasard pour des observations dépendantes, Statistique et Analyse des Données, Volume 10 (1985), pp. 42-49 | Numdam | MR | Zbl

[21] Cohen, M.P.; Kuo, L. The admissibility of the empirical distribution function, The Annals of Statistics, Volume 13 (1985), pp. 262-271 | MR | Zbl

[22] Cleveland, W.S. Robust locally weighted regression and smoothing scatterplots, Journal of the American Statistical Association, Volume 74 (1979), pp. 829-836 | MR | Zbl

[23] Cox, D.R. Some sampling problems in technology, New Developments in Survey Sampling (Johnson, N. L.; Smith, H., eds.), Wiley, New-York, 1969

[24] Cheng, M.-Y.; Peng, L. Regression modelling for nonparametric estimation of distribution and quantiles functions, Statistica Sinica, Volume 12 (2002), pp. 1043-1060 | MR | Zbl

[25] Caperaa, P.; Van Cutsem, B. Méthodes et modèles en statistique non paramétrique, Bordas, Paris, 1988 | MR | Zbl

[26] Devroye, L. A Course in Density Estimation, Birkhäuser, Boston, 1987 | MR | Zbl

[27] Devroye, L.; Györfi, L. Distribution and density estimation, CISM Courses and Lectures, Volume 434 (2002), pp. 221-270 | MR

[28] Donoho, D.L.; Johnstone, I.M.; Kerkyacharian, G.; Picard, D. Density estimation by wavelet thresholding, The Annals of Statistics, Volume 24 (1996), pp. 508-539 | MR | Zbl

[29] Dvoretzky, A.; Kiefer, J.C.; Wolfowitz, J. Asymptotic minimax character of the sample distribution function and of the classical multinomial estimator, The Annals of Mathematical Statistics, Volume 33 (1956), pp. 642-669 | MR | Zbl

[30] Devroye, L.; Lugosi, G. Combinatorial Methods in Density Estimation, Springer, New-York, 2001 | MR | Zbl

[31] Donsker, M.D. Justification and extension of Doob’s heuristic approach to the Kolmogorov-Smirnov theorems, The Annals of Mathematical Statistics, Volume 23 (1952), pp. 277-281 | MR | Zbl

[32] Doob, J. Heuristic approach to the Kolmogorov-Smirnov theorm, The Annals of Mathematical Statistics, Volume 20 (1949), pp. 393-403 | MR | Zbl

[33] Doob, J. Stochastic processes, Wiley, New-York, 1953 | MR | Zbl

[34] Delecroix, M.; Simioni, M.; Thomas-Agnan, C. Functional estimation under shape constraints, Journal of Nonparametrics Statistics, Volume 6 (1996), pp. 69-89 | MR | Zbl

[35] Devroye, L.; Wise, G.L. On the recovery of discrete probability densities from imperfect measurements, Journal of the Franklin Institute, Volume 307 (1979), pp. 1-20 | MR | Zbl

[36] Efromovich, S. Distribution estimation for biased data, Journal of Statistical Planning and Inference, Volume 124 (2004), pp. 1-43 | MR | Zbl

[37] Epanechnikov, A.A. Nonparametric estimation of a multivariate probability density, Theory of Probability and its Applications, Volume 14 (1969), pp. 153-158 | MR | Zbl

[38] Efron, B.; Tibshirani, R.J. An introduction to the Bootstrap, Chapman & Hall, London, 1993 | MR | Zbl

[39] Falk, M. Relative efficiency and deficiency of kernel type estimators of smooth distribution functions, Statistica Neerlandica, Volume 37 (1983), pp. 73-83 | MR | Zbl

[40] Falk, M. Relative deficiency of kernel type estimators of quantiles, The Annals of Statistics, Volume 12 (1984), pp. 261-268 | MR | Zbl

[41] Fan, J. Design-adaptive nonparametric regression, Journal of the American Statistical Association, Volume 87 (1992), pp. 998-1004 | MR | Zbl

[42] Fan, J. Local linear regression smoothers and their minimax efficiencies, The Annals of Statistics, Volume 21 (1993), pp. 196-216 | MR | Zbl

[43] Ferrigno, S.; Ducharme, G. A global test of goodness-of-fit for the conditional distribution function, Comptes Rendus Mathématiques de l’Académie des Sciences de Paris, Volume 341 (2005), pp. 313-316 | MR | Zbl

[44] Fernholz, L.T. Almost sure convergence of smoothed empirical distribution functions, Scandinavian Journal of Statistics, Volume 18 (1991), pp. 255-262 | MR | Zbl

[45] Fan, J.; Gijbels, I. Variable bandwidth and local linear regression smoothers, The Annals of Statistics, Volume 20 (1992), pp. 2008-2036 | MR | Zbl

[46] Fan, J.; Gijbels, I. Local polynomial modelling and its applications, Chapman & Hall, London, 1996 | MR | Zbl

[47] Friedman, Y.; Gelman, A.; Phadia, E. Best invariant estimation of a distribution function under the Kolmogorov-Smirnov loss function, The Annals of Statistics, Volume 16 (1988), pp. 1254-1261 | MR | Zbl

[48] Foldes, A.; Revesz, P. A general method for density estimation, Studia Scientiarum Mathematicarum, Volume 9 (1974), pp. 81-92 | MR | Zbl

[49] Forte, B.; Vrscay, E.R. Solving the inverse problem for function/image approximation using iterated function systems, Fractals, Volume 2 (1995), pp. 325-334 | MR | Zbl

[50] Golubev, G.K.; Levit, B.Y. Distribution function estimation : adaptive smoothing, Mathematical Methods of Statistic, Volume 5 (1996), pp. 383-403 | MR | Zbl

[51] Gasser, T.; Müller, H.G. Estimating regression function and their derivatives by the kernel method, Scandinavian Journal of Statistics, Volume 3 (1984), pp. 171-185 | MR | Zbl

[52] Grenander, U. On the theory of mortality measurement part II, Skandinavisk Aktuarietidskrift, Volume 39 (1956), pp. 125-153 | MR | Zbl

[53] Green, P.J.; Silverman, B.W. Nonparametric Regression and Generalized Linear Models. A Roughness Penalty Approach, Chapman & Hall, London, 1994 | Zbl

[54] Huang, M.L.; Brill, P.H. A distribution estimation method based on level crossings, Journal of Statistical Planning and Inference, Volume 124 (2004), pp. 45-62 | Zbl

[55] Härdle, W.; Kerkyacharian, G.; Picard, D.; Tsybakov, A. Wavelets, Approximation and Statisticals Applications, Lecture Notes in Statististics, Volume 129 (1999) | Zbl

[56] Herrick, D.R.M.; Nason, G.P.; Silverman, B.W. Some new methods for wavelet density estimation, Sankhya, Volume A63 (2001), pp. 394-411 | Zbl

[57] Hennequin, P.L.; Tortrat, A. Théorie des Probabilités et Quelques applications, Masson, Paris, 1965 | Zbl

[58] Hu, I. A uniform bound for the tail probability of Kolmogorov-Smirnov statistics, The Annals of Statistics, Volume 13 (1985), pp. 811-826 | Zbl

[59] Hall, P.; Wolff, R.C.L.; Yao, Q. Methods for estimating a conditional distribution function, Journal of the American Statistical Association, Volume 94 (1999), pp. 154-163 | Zbl

[60] Iacus, S.M; La Torre, D. A comparative simulation study on the IFS distribution function estimator, Nonlinear Analysis : Real World Applications, Volume 6 (2005), pp. 858-873 | Zbl

[61] Jones, M.C. The performance of kernel density functions in kernel distribution function estimation, Statistics and Probability Letters, Volume 9 (1990), pp. 129-132 | Zbl

[62] Korwar, R.M.; Hollander, M. Empirical Bayes estimation of a distribution function, The Annals of Statistics, Volume 4 (1976), pp. 581-588 | Zbl

[63] Kolmogorov, A.N. Sulla determinazione empirica di una legge de distribuzione, Giornale dell’Instituto Italiano degli Attuari, Volume 4 (1933), pp. 83-91 | JFM | Zbl

[64] Kiefer, J.C.; Wolfowitz, J. Consistency of the maximum likelihood estimator in the presence of infinitely many nuisance parameters, The Annals of Mathematical Statistics, Volume 27 (1956), pp. 887-906 | Zbl

[65] Leadbetter, M.R. Point processes generated by level crossings, Stochastic Point processes : Statistical Analysis, Theory and Applications (Lewis, P.A.W., ed.), Wiley-Interscience, New-York, 1972 | Zbl

[66] Lehmann, E.L. Theory of Point Estimation, Wiley, New-York, 1983 | Zbl

[67] Lejeune, M.; Sarda, P. Smooth estimators of distribution and density functions, Computational Statistics and Data Analysis, Volume 14 (1992), pp. 457-471 | Zbl

[68] Massart, P. The tight constant in the Dvoretzky-Kiefer-Wolfowitz inequality, The Annals of Probability, Volume 18 (1990), pp. 1269-1283 | Zbl

[69] Mohamed, R.M.; El-Baz, A.; Farag, A.A. Probability density estimation using advanced support vector machines and the EM algorithm, International Journal of Signal Processing, Volume 1 (2004), pp. 260-264

[70] Mohamed, R.M.; Farag, A.A. Mean field theory for density estimation using support vector machines, Seventh International Conference on Information Fusion, Stockholm (2004), pp. 495-501

[71] Modarres, R. Efficient nonparametric estimation of a distribution function, Computational Statistics and Data Analysis, Volume 39 (2002), pp. 75-95 | Zbl

[72] Nadaraya, E.A. Some new estimates for distribution function, Theory of Probability and its Application, Volume 9 (1964), pp. 497-500 | Zbl

[73] Parzen, E. On the estimation of a probability density and mode, The Annals of Mathematical Statistics, Volume 33 (1962), pp. 1065-1076 | Zbl

[74] Phadia, E.G. Minimax estimation of a cumulative distribution function, The Annals of Statistics, Volume 1 (1973), pp. 1149-1157 | Zbl

[75] Pantazopoulos, S.N.; Pappis, C.P.; Fifis, T.; Costopoulos, C.; Vaughan, J.A.; Gasparini, M. Nonparametric Bayes estimation of a distribution function with truncated data, Journal of Statistical Planning and Inference, Volume 55 (1996), pp. 361-369

[76] Patil, G.P.; Rao, C.R.; Zelen, M. Weighted distribution, Encyclopedia of Statistical Sciences (Johnson, N. L.; Kotz, S., eds.), Wiley, New-York, 1988

[77] Reiss, R.-D. Nonparametric estimation of smooth distribution functions, Scandinavian Journal of Statistics, Volume 8 (1981), pp. 116-119 | Zbl

[78] Restle, E.M. Estimating cumulative distributions by spline smoothing, Ecole Polytechnique Fédérale de Lausanne (2001) (Ph. D. Thesis)

[79] Robert, C.P. L’Analyse Statistique Bayésienne, Economica, Paris, 1992 | Zbl

[80] Rosenblatt, M. Remarks on some non-parametric estimates of a density function, The Annals of Mathematical Statistics, Volume 27 (1956), pp. 832-837 | Zbl

[81] Roussas, G.G. Nonparametric estimation of the transition distribution function of a Markov process, The Annals of Mathematical Statistics, Volume 40 (1969), pp. 1386-1400 | Zbl

[82] Samanta, M. Non-parametric estimation of conditional quantiles, Statistics and Probability Letters, Volume 7 (1989), pp. 407-412 | Zbl

[83] Schölkopf, B.; Burges, C.J.C.; Smola, A.J. Advances in Kernel methods. Support vector learning, MIT Press, 1999 | Zbl

[84] Shirahata, S.; Chu, I.-S. Integrated squared error of kernel-type estimator of distribution function, Annals of the Institute of Statistical Mathematics, Volume 44 (1992), pp. 579-591 | Zbl

[85] Singh, R. S.; Gasser, T.; Prasad, B. Nonparametric estimates of distributions functions, Communication in Statistics - Theory and Methods, Volume 12 (1983), pp. 2095-2108 | Zbl

[86] Smirnov, N.V. Approximate laws of distribution of random variables from empirical data, Uspekhi Matematicheskikh Nauk, Volume 10 (1944), pp. 179-206

[87] Schölkopf, B.; Smola, A.J. Learning With Kernels : Support Vector Machines, Regularization, Optimization and Beyond, MIT Press, 2002

[88] Stone, C.J. Consistent nonparametric regression, The Annals of Statistics, Volume 5 (1977), pp. 595-645 | Zbl

[89] Stute, W. Asymptotic normality of nearest neighbor regression function estimates, The Annals of Statistics, Volume 12 (1984), pp. 917-926 | Zbl

[90] Stute, W. Conditionnal empirical processes, The Annals of Statistics, Volume 14 (1986), pp. 638-647 | Zbl

[91] Susarla, V.; Van Ryzin, J. Empirical Bayes estimation of a distribution (survival) function from right censored observations, The Annals of Statistics, Volume 6 (1978), pp. 740-754 | Zbl

[92] Shorack, G.R.; Wellner, J.A. Empirical Processes with Applications to Statistics, Wiley, New-York, 1986 | Zbl

[93] Swanepoel, J.W.H.. Mean integrated squared error properties and optimal kernels when estimating a distribution function, Communication in Statistics - Theory and Methods, Volume 17 (1988), p. 3785-379 | Zbl

[94] Vapnik, V. The nature of statistical learning theory, Springer Verlag, New-York, 1995 | Zbl

[95] Vapnik, V.; Kotz, S. Estimation on dependences based on empirical data, Springer Verlag, New-York, 2006 | Zbl

[96] Wahba, G. Spline models for observational data, Society for Industrial and Applied Mathematics (SIAM), Philadelphia, 1990 | Zbl

[97] Winter, B.B. Strong uniform consistency of integrals of density estimators, The Canadian Journal of Statistics, Volume 1 (1973), pp. 247-253 | Zbl

[98] Winter, B.B. Convergence rate of perturbed empirical distribution functions, Journal of Applied Probability, Volume 16 (1979), pp. 163-173 | Zbl

[99] Watson, G.S.; Leadbetter, M.R. Hazard analysis II, Sankhya, Volume 26 (1964), pp. 101-116 | Zbl

[100] Wright, I.W.; Wegman, E.J. Isotonic, convex and related splines, The Annals of Statistics, Volume 8 (1980), pp. 1023-1035 | Zbl

[101] Yamato, H. Uniform convergence of an estimator of a distribution function, Bulletin on Mathematical Statistics, Volume 15 (1973), pp. 69-78 | Zbl

[102] Yu, Q.Q. Inadmissibility of the empirical distribution function in continuous invariant problems, The Annals of Statistics, Volume 17 (1989), pp. 1347-1359 | Zbl