Hasil untuk "math.ST"

Jean-Christophe Pain

We derive a closed-form solution for the Kullback-Leibler divergence between two Fréchet extreme-value distributions. The resulting expression is rather simple and involves the Euler-Mascheroni constant.

Vincent Divol

We provide a short proof that the Wasserstein distance between the empirical measure of a n-sample and the estimated measure is of order n^-(1/d), if the measure has a lower and upper bounded density on the d-dimensional flat torus.

Mueen-ud-Din Azad, Muhammad Mohsin

The significance of Marshall-Olkin distribution in reliability theory has motivated us to introduce a generalized exponentiated Marshall-Olkin (GEMO), a family of distributions.

Y. Boularouk, K. Djaballah

Strong consistency of the quasi-maximum likelihood estimator is given for a general class of multidimensional causal processes based on asyMmetric laplacian innovation.

Dimbihery Rabenoro

In this paper, we prove a conditional limit theorem for independent not necessarily identically distributed random variables. Namely, we obtain the asymptotic distribution of a large number of them given the sum.

Johannes Tewes

We consider long-range dependent data. It is shown that the bootstrapped empirical process of these data converges to a semi-degenerate limit. The random part of this limit is always Gaussian. Thus the bootstrap might fail when the original empirical process accomplishes a noncentral limit theorem.

Félix Balazard

Matching, the stratification of observations, is of primary importance for the analysis of observational studies. We show that the score test of conditional logistic regression and the paired Student/Hotelling test, two tests for paired data, are asymptotically equivalent.

Norbert Henze, Stefan Koch

We provide the lacking theory for a test of normality based on the empirical moment generating function.

Arturo Erdely

In this brief note we prove that linear B-spline copulas is not a new family of copulas since they are equivalent to checkerboard copulas, and discuss in particular how they are used to extend empirical subcopulas to copulas.

Milan Stehlik, Philipp Hermann

This is "Letter to the Editor" of Annals of Applied Statistics, addressing the paper by Goerg G. M. (2011) "Lambert W random variables-a new family of generalized skewed distributions with applications to risk estimation".

Larry Wasserman

Discussion of "A significance test for the lasso" by Richard Lockhart, Jonathan Taylor, Ryan J. Tibshirani, Robert Tibshirani [arXiv:1301.7161].

A. Buja, L. Brown

Discussion of "A significance test for the lasso" by Richard Lockhart, Jonathan Taylor, Ryan J. Tibshirani, Robert Tibshirani [arXiv:1301.7161].

Jochen Fiedler

We show that the even- resp. odd-dimensional Schoenberg coefficients in Gegenbauer expansions of isotropic positive definite functions on the d-sphere can be expressed as linear combinations of Fourier resp. Legendre coefficients, and we give closed form expressions for the coefficients involved in these expansions.

Alvaro Sandroni, Eran Shmaya

We construct a prequential test of probabilistic forecasts that does not reject correct forecasts when the data-generating processes is exchangeable and is not manipulable by a false forecaster.

Chunsheng Ma

It is not the purpose of this correspondence to complain about that six out of seven theorems listed in Porcu and Schilling (arXiv:0812.2936; 2011, Bernoulli) belong to others, but not to the authors themselves. This is simply a call for the priority, originality, and correctness.

Sylvain Le Corff, Gersende Fort

This is a supplementary material to the paper "Online Expectation Maximization based algorithms for inference in hidden Markov models". It contains further technical derivations and additional simulation results.

Mohamed Cherfi

In this paper we prove large deviations principles for the Nadaraya-Watson estimator of the regression of a real-valued variable with a functional covariate. Under suitable conditions, we show pointwise and uniform large deviations theorems with good rate functions.

Shanti Venetiaan

In this paper a different approach to consider third and fourth order efficiency is suggested for non symmetric cases. Fourth order efficiency does not follow automatically but only after some adjustments are made.

Mikhail Kovtun, Anatoliy Yashin, Igor Akushevich

We establish necessary and sufficient conditions for consistency of estimators of mixing distribution in linear latent structure analysis.

André Mas, Besnik Pumo

We introduce and study a new model for functional data. The ARHD is an autoregressive model in which the first order derivative of the random curves appears explicitely. Convergent estimates are obtained through a double penalization method. A simluation and a real case study follow as well as comparisons with other recent techniques.