The bottom part of Table 3 shows the results of the tests on the correlations.
Only one article scored excellent on hypothesis testing of the correlation between the MHHS and SF-36 [ 20].
The proportional hazards assumption was examined by statistical testing of the correlation between weighted Schoenfeld residuals and logarithmically transformed survival time.
Given that the assumptions of Peto's paradox are not supported by strong evidence, our review suggests alternative ways for a more robust testing of the correlation (or rather lack of it) between body size and cancer risk.
Statistical significance tests of the correlations provide a conservative estimate of the degree of randomness.
To formally test the proportional hazards model assumption that the HR is proportional over time, we conducted post-estimation tests of the correlations between Schoenfeld residuals from each multivariate model and time (Cleves et al, 2006).
Tests of the correlation between proteinuria and mRNA expression were performed by relating the normalized mRNA expression values to proteinuria using Pearson correlation.
A decision to qualify a given correlation as stable or stress-specific must thereby be supported by both the correlation significance test and the homogeneity test of the correlation coefficient's distribution in all experimental conditions.
Since large sample correlation tests are potentially vulnerable to deviations from normality, we also conducted a permutation test of the correlation between STX1A and PC1 by permuting PC1 across subjects one million times (SPSS 15.0) (Fig. 3b).
Spearman's test of the correlation of PTEN mRNA levels and PIK3CA mutations was applied (N.S., not significant).
