Aggregated test of independence based on HSIC measures

02/18/2019
by   Anouar Meynaoui, et al.
0

Dependence measures based on reproducing kernel Hilbert spaces, also known as Hilbert-Schmidt Independence Criterion and denoted HSIC, are widely used to statistically decide whether or not two random vectors are dependent. Recently, non-parametric HSIC-based statistical tests of independence have been performed. However, these tests lead to the question of prior choice of the kernels associated to HSIC, there is as yet no method to objectively select specific kernels. In order to avoid a particular kernel choice, we propose a new HSIC-based aggregated procedure allowing to take into account several Gaus-sian kernels. To achieve this, we first propose non-asymptotic single tests of level α ∈ (0, 1) and second type error controlled by β ∈ (0, 1). We also provide a sharp upper bound of the uniform seperation rate of the proposed tests. Thereafter, we introduce a multiple testing procedure in the case of Gaussian kernels, considering a set of various parameters. These agregated tests are shown to be of level α and to overperform single tests in terms of uniform separation rates.

READ FULL TEXT
research
08/31/2022

A general framework for the analysis of kernel-based tests

Kernel-based tests provide a simple yet effective framework that use the...
research
04/05/2019

Aggregated kernel based tests for signal detection in a regression model

Considering a regression model, we address the question of testing the n...
research
06/25/2016

Large-Scale Kernel Methods for Independence Testing

Representations of probability measures in reproducing kernel Hilbert sp...
research
10/12/2016

Post Selection Inference with Kernels

We propose a novel kernel based post selection inference (PSI) algorithm...
research
11/17/2016

Fast Non-Parametric Tests of Relative Dependency and Similarity

We introduce two novel non-parametric statistical hypothesis tests. The ...
research
06/10/2013

A Kernel Test for Three-Variable Interactions

We introduce kernel nonparametric tests for Lancaster three-variable int...
research
06/03/2022

Angle Based Dependence Measures in Metric Spaces

In this article, we introduce a general framework of angle based indepen...

Please sign up or login with your details

Forgot password? Click here to reset