Table 3.
Pearson correlation coefficients for equal and disjoint gene groups
Equal | ||||||||
Pearson | Spearman | |||||||
Platform A | Platform B | N | r | 95% CI | P-value | r | 95% CI | P-value |
Affymetrix | Agilent | 966 | 0.769 | .742 < p < .794 | <0.0001 | 0.783 | .757 < p < .8058 | <0.0001 |
Affymetrix | Codelink | 1263 | 0.73 | .703 < p < .755 | <0.0001 | 0.745 | .719 < p < .769 | <0.0001 |
Agilent | Codelink | 908 | 0.662 | .624 < p < .697 | <0.0001 | 0.652 | .613 < p < .688 | <0.0001 |
Disjoint | ||||||||
Pearson | Spearman | |||||||
Platform A | Platform B | N | r | 95% CI | P-value | r | 95% CI | P-value |
Affymetrix | Agilent | 101 | 0.506 | .344 < p < .638 | <0.0001 | 0.53 | .373 < p < .658 | <0.0001 |
Affymetrix | Codelink | 49 | 0.246 | -0.03 < p < .493 | 0.0889 | 0.28 | -0.0009 < p < 0.521 | 0.051 |
Agilent | Codelink | 114 | 0.282 | .104 < p < .443 | 0.0023 | 0.242 | .061 < p < .408 | 0.0095 |
r – correlation coefficient
95% CI – rho is the 95% confidence interval around r calculated using Fisher's transform
p-value – value for testing the hypothesis of no correlation against the alternative that there is a non-zero correlation
n – number of genes in each pairing used in correlation calculation