Estimating the joint distribution of independent categorical variables via model selection
Durot, C. ; Lebarbier, E. ; Tocquet, A.-S.
Bernoulli, Tome 15 (2009) no. 1, p. 475-507 / Harvested from Project Euclid
Assume one observes independent categorical variables or, equivalently, one observes the corresponding multinomial variables. Estimating the distribution of the observed sequence amounts to estimating the expectation of the multinomial sequence. A new estimator for this mean is proposed that is nonparametric, non-asymptotic and implementable even for large sequences. It is a penalized least-squares estimator based on wavelets, with a penalization term inspired by papers of Birgé and Massart. The estimator is proved to satisfy an oracle inequality and to be adaptive in the minimax sense over a class of Besov bodies. The method is embedded in a general framework which allows us to recover also an existing method for segmentation. Beyond theoretical results, a simulation study is reported and an application on real data is provided.
Publié le : 2009-05-15
Classification:  adaptive estimator,  categorical variable,  least-squares estimator,  model selection,  multinomial variable,  penalized minimum contrast estimator,  wavelet
@article{1241444899,
     author = {Durot, C. and Lebarbier, E. and Tocquet, A.-S.},
     title = {Estimating the joint distribution of independent categorical variables via model selection},
     journal = {Bernoulli},
     volume = {15},
     number = {1},
     year = {2009},
     pages = { 475-507},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1241444899}
}
Durot, C.; Lebarbier, E.; Tocquet, A.-S. Estimating the joint distribution of independent categorical variables via model selection. Bernoulli, Tome 15 (2009) no. 1, pp.  475-507. http://gdmltest.u-ga.fr/item/1241444899/