Skip to main content

Table 1 Empirical type I errors for n=100, 200, or 500

From: MiRKAT-S: a community-level test of association between the microbiota and survival times

Number

K w

K u

K 0.5

K BC

100

0.0544

0.0540

0.0530

0.0542

200

0.0494

0.0480

0.0470

0.0462

500

0.0506

0.0478

0.0536

0.0442

  1. Empirical type I errors for sample sizes n=100, 200, and 500 with approximately 25% censoring. Results are based on 5000 simulated datasets. K w, K u, K BC, and K 0.5 represent results for the weighted UniFrac kernel, unweighted UniFrac kernel, Bray-Curtis kernel, and generalized UniFrac kernel with α=0.5, respectively
Back to article page

Microbiome

ISSN: 2049-2618

Contact us