Back to metrics

ASW

🎯 Clustering & Cell Type Discovery

Silhouette Score (Average)

Direction

Higher is Better

Value Range

[-1, 1]

Category

Clustering & Cell Type Discovery

Supervised metrics comparing predicted clusters to ground truth labels

Description

Average silhouette coefficient measuring cluster cohesion and separation

Mathematical Formula

ASW = (1/n) * Σ(b_i - a_i) / max(a_i, b_i)

Interpretation Guide

Range [-1, 1]. 1 = well-separated clusters, 0 = overlapping clusters, -1 = incorrect assignments. Measures geometric cluster quality.

Related Metrics

Other metrics in the Clustering & Cell Type Discovery category