PulseAugur
EN
LIVE 11:22:36

New ERICA framework quantifies replicability of cluster analysis

Researchers have introduced ERICA, a new framework designed to quantitatively assess the replicability of cluster analysis results. This method generates a statistic to determine if identified clusters are consistently found across analyses. While ERICA demonstrated replicable cluster discovery on synthetic data, it highlighted potential for non-replicable findings when applied to real-world gene expression datasets for breast cancer subtype validation, emphasizing the need for rigorous inspection. AI

IMPACT Provides a new quantitative tool for evaluating the reliability of clustering algorithms, crucial for scientific discovery.

RANK_REASON The cluster contains an academic paper detailing a new methodology for cluster analysis. [lever_c_demoted from research: ic=1 ai=1.0]

Read on arXiv stat.ML →

AI-generated summary · Google Gemini · from 1 sources. How we write summaries →

COVERAGE [1]

  1. arXiv stat.ML TIER_1 English(EN) · Siamak K. Sorooshyari, Manuel A. Rivas, Robert Tibshirani ·

    ERICA: Quantifying Replicability of Cluster Analysis

    arXiv:2606.00302v1 Announce Type: new Abstract: Despite being ubiquitous in science, clustering remains a technique whose results are not quantitatively scrutinized via a framework. We present an analysis called evaluating replicability via iterative clustering assignments (ERICA…