3,832
Views
6
CrossRef citations to date
0
Altmetric
Research Article

A robust Spearman correlation coefficient permutation test

&
Pages 2141-2153 | Received 30 Nov 2021, Accepted 29 Aug 2022, Published online: 09 Sep 2022

Figures & data

Table 1. Type I error rate of testing H0:ρs=0 versus H0:ρs>0.

Figure 1. Contour plots for the density of a synthetic data set (n = 10, 000) for each simulation distribution.

Figure 1. Contour plots for the density of a synthetic data set (n = 10, 000) for each simulation distribution.

Figure 2. Type I error rate of testing H0:ρs=0 versus H1:ρs>0.

Figure 2. Type I error rate of testing H0:ρs=0 versus H1:ρs>0.

Table 2. Power of testing H0:ρs=0 versus H0:ρs>0 under bivariate normal distributions.

Figure 3. Scatter plot of log-transformed TP53 versus FGFR1 abundance for TCGA data (a), and age versus log(PSA) for the PSA data (b).

Figure 3. Scatter plot of log-transformed TP53 versus FGFR1 abundance for TCGA data (a), and age versus − log (PSA) for the PSA data (b).

Table 3. Results of testing H0:ρs=0 versus H1:ρs>0 for TCGA breast cancer data and PSA data.