Xavier Gendre (2014)
ESAIM: Probability and Statistics
Similarity:
Let ∈ ℝ be a random vector with mean and covariance matrix where is some known × -matrix. We construct a statistical procedure to estimate as well as under moment condition on or Gaussian hypothesis. Both cases are developed for known or unknown . Our approach is free from any prior assumption on and is based on non-asymptotic model selection methods....
Elena Di Bernardino, Thomas Laloë, Véronique Maume-Deschamps, Clémentine Prieur (2013)
ESAIM: Probability and Statistics
Similarity:
This paper deals with the problem of estimating the level sets () = {() ≥ }, with ∈ (0,1), of an unknown distribution function on ℝ . A plug-in approach is followed. That is, given a consistent estimator of , we estimate () by () = { () ≥ }. In our setting, non-compactness property is required for the level sets to estimate. We state consistency results with respect to the Hausdorff distance and the volume of the symmetric...
Jérôme Dedecker, Adeline Samson, Marie-Luce Taupin (2014)
ESAIM: Probability and Statistics
Similarity:
Consider an autoregressive model with measurement error: we observe = + , where the unobserved is a stationary solution of the autoregressive equation = ( ) + . The regression function is known up to a finite dimensional parameter to be estimated. The distributions of and are unknown and...
Matthieu Lerasle (2012)
ESAIM: Probability and Statistics
Similarity:
We build confidence balls for the common density of a real valued sample . We use resampling methods to estimate the projection of onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all ≥ 2 and the balls are adaptive over a collection of linear spaces.
Matthieu Lerasle (2012)
ESAIM: Probability and Statistics
Similarity:
We build confidence balls for the common density of a real valued sample . We use resampling methods to estimate the projection of onto finite dimensional linear spaces and a model selection procedure to choose an optimal approximation space. The covering property is ensured for all ≥ 2 and the balls are adaptive over a collection of linear spaces.
Tze Leng Lai, Qi-Man Shao, Qiying Wang (2011)
ESAIM: Probability and Statistics
Similarity:
Let be a Studentized U-statistic. It is proved that a Cramér type moderate deviation ( ≥ )/(1 − Φ()) → 1 holds uniformly in ∈ [0, ( )) when the kernel satisfies some regular conditions.
Sandrine Péché (2012)
Annales de l'I.H.P. Probabilités et statistiques
Similarity:
We consider complex sample covariance matrices = (1/)* where is a × random matrix with i.i.d. entries , 1 ≤ ≤ , 1 ≤ ≤ , with distribution . Under some regularity and decay assumptions on , we prove universality of some local eigenvalue statistics in the bulk of the spectrum in the limit where → ∞ and lim→∞ / = for any real number ∈ (0, ∞).
Luís Balsa Bicho, António Ornelas (2014)
ESAIM: Control, Optimisation and Calculus of Variations
Similarity:
We prove of vector minimizers () = (||) to multiple integrals ∫ ((), |()|) on a ⊂ ℝ, among the Sobolev functions (·) in + (, ℝ), using a : ℝ×ℝ → [0,∞] with (·) and . Besides such basic hypotheses, (·,·) is assumed to satisfy also...
Fábio Júlio Valentim (2012)
Annales de l'I.H.P. Probabilités et statistiques
Similarity:
Fix a polynomial of the form () = + ∑2≤≤ =1 with (1) gt; 0. We prove that the evolution, on the diffusive scale, of the empirical density of exclusion processes on , with conductances given by special class of functions, is described by the unique weak solution of the non-linear parabolic partial differential equation = ∑ ...
Nabil Rachdi, Jean-Claude Fort, Thierry Klein (2013)
ESAIM: Probability and Statistics
Similarity:
In this paper, we consider a new framework where two types of data are available: experimental data supposed to be i.i.d from and outputs from a simulated reduced model. We develop a procedure for parameter estimation to characterize a feature of the phenomenon . We prove a risk bound qualifying the proposed procedure in terms of the number of experimental data , reduced model complexity...
Marc Arnaudon, Laurent Miclo (2014)
ESAIM: Probability and Statistics
Similarity:
Let be a complete Riemannian manifold, ∈ ℕ and ≥ 1. We prove that almost everywhere on = ( ,, ) ∈ for Lebesgue measure in , the measure μ ( x ) = 1 N ∑ k = 1 N δ x k has a unique–mean (). As a consequence, if = ( ,, ) is a -valued random variable with absolutely continuous law, then almost surely (()) has a unique –mean. In particular if ( ...
Arturo Carpi, Aldo de Luca (2010)
RAIRO - Theoretical Informatics and Applications
Similarity:
For any finite word on a finite alphabet, we consider the basic parameters and of defined as follows: is the minimal natural number for which has no right special factor of length and is the minimal natural number for which has no repeated suffix of length . In this paper we study the distributions of these parameters, here called characteristic parameters, among the words ...
József Balogh, Béla Bollobás (2010)
RAIRO - Theoretical Informatics and Applications
Similarity:
Let be a hereditary property of words, , an infinite class of finite words such that every subword (block) of a word belonging to is also in . Extending the classical Morse-Hedlund theorem, we show that either contains at least words of length for every or, for some , it contains at most words of length for every . More importantly, we prove the following quantitative extension of this result: if has words of length then, for every , it contains at most ⌈( + 1)/2⌉⌈( + 1)/2⌈...
Gaëlle Chagny (2013)
ESAIM: Probability and Statistics
Similarity:
This paper deals with the problem of estimating a regression function , in a random design framework. We build and study two adaptive estimators based on model selection, applied with warped bases. We start with a collection of finite dimensional linear spaces, spanned by orthonormal bases. Instead of expanding directly the target function on these bases, we rather consider the expansion of = ∘ , where is the cumulative distribution function of the design, following...
Christopher S. Withers, Saralees Nadarajah (2013)
ESAIM: Probability and Statistics
Similarity:
Consider testing : ∈ against : ∈ for a random sample , ..., from , where and are two disjoint sets of cdfs on ℝ = (−∞, ∞). Two non-local types of efficiencies, referred to as the fixed- and fixed- efficiencies, are introduced for this two-hypothesis testing situation. Theoretical tools are developed to evaluate these efficiencies for some of the most...