Spearman’s rank -order correlation

The 28 toxoplasma-positive sera that had been titrated for antibody by FA were titrated by RIA, and the titers of the two tests were correlated, using Spearman s rank-order correlation test. The correlation coefficient was 0.68, and probability that this value differs from zero (no correlation) by chance alone was <0.001. Thus there was reasonably good agreement between the titers obtained in the two tests. 

If correlation analysis is used with the raw data, ideally both data types should have similar ranges and distributions. If data is directly linearly correlated, this can be neglected, but is rarely the case for metabolome and transcriptome data. Changes in gene expression may not alter metabolite pools significantly. Therefore, data have to be normalized in an appropriate way and correlation methods other than linear correlation have to be used (e.g., Spearman s rank-order correlation or Kendall rank correlation should be preferred over Pearson correlation). 

One-way analysis of variance (ANOVA) was used for assessment of the differences among groups and subgroups of subjects. Spearman s rank order correlations were used for analyses of the relationships between isoflavones and thyroid hormone parameters. 

For the statistical analysis, the results for each test specimen were coded either one for a pass (i.e., no liquid penetration) or zero for a failure. The effects of fabric type and challenge liquid on the liquid penetration of the fabrics were analyzed using separate two-way analyses of variance, Fisher s LSD post hoc comparison tests, and Spearman s rank order correlations. The level of statistical significance was set at 0.05. The statistical tables and raw data are available in the technical report (8). 

---