Skip to main content

Table 2 Comparison between the significance levels of the correlations for the made up data-sets and 2500 random samples produced based on the specifications of Table 1*

From: How does correlation structure differ between real and fabricated data-sets?

P-value

p ≤ 0.05

0.05 <p ≤ 0.10

p > 0.10

Total

Data-set

    

Made up

24 (70.6%)

3 (8.8%)

7 (20.6%)

34

Simulated

137 (5.5%)

125 (5.0%)

2238 (89.5%)

2500

  1. * data-sets with p-value ≤ 0.05 were compared with p-value > 0.05, (Fisher's exact test, p < 0.0001)
Back to article page

BMC Medical Research Methodology

ISSN: 1471-2288

Contact us