Synapse
⌘+K
Synapse
PulseExploreJournal ClubResearchersJournals
Instagram
HomeJournal ClubExplore
March 26, 2026Scandinavian Journal of Statistics

Powerful kernel‐based association tests for multivariate responses

View Full Paper
Ask AI
Bookmark
Share

Authors

MLM. G. LongYSYuke ShiLSLiuquan Sun

Discussion

Loading...

Member takes

Overview

Innovative kernel-based tests show improved independence detection in multivariate data, suggesting better analytical tools.

Key Points

  • The aim is to develop effective kernel-based tests for analyzing independence in multivariate response data.
  • Introduced kernel-based independence tests in the framework of reproducing kernel Hilbert spaces (RKHS).
  • Developed two tests: Maximal Kernel-based Independence Test (MKIT) and Maximin Efficient Robust Test (MERT).
  • Derived explicit sample-level expressions and studied their asymptotic null distributions.
  • Conducted extensive simulations to evaluate the performance of the proposed tests.
  • MKIT and MERT are shown to outperform existing methods in various analytical scenarios.
  • MKIT conforms to the extreme-value type I-Gumbel distribution, while MERT aligns with the normal distribution.
  • Simulations indicate strong statistical power for MKIT and MERT.

Cite This Study

Long et al. (2026) studied this question.

synapsesocial.com/papers/69c4cc85fdc3bde448917e86https://doi.org/10.1111/sjos.70064
View Full Paper
Ask AI
Bookmark
Share

Also Consider

Synapse has enriched 3 closely related papers on similar clinical questions. Consider them for comparative context:

  1. 1Partially functional linear regression in high dimensions2016 · 175 citations
  2. 2The orbitofrontal cortex: reward, emotion and depression2020 · 491 citations
  3. 3The Use of Maximum Likelihood Estimates in $\chi^2$ Tests for Goodness of Fit1954 · 556 citations