# Spearman's correlation network

The Spearman correlation coefficient is calculated for each pairwise combination of markers. Statistical significance for connections between markers is calculated exactly using Algorithm AS89 [Best & Roberts 1975 J. Roy. Stat. Soc. C App. 24:377] for datasets with <1290 patients or an approximation using a Student's t distribution otherwise. Multiple hypothesis correction is performed according to Benjamini-Yekutieli FDR [Benjamini & Yekutieli 2001 Ann. Statist. 29:1165] (default) or Bonferroni to give a corrected p-value. The result is displayed as a network (a plot of markers connected pairwise by edges/lines) with a default significance threshold of FDR p≤0.05. The threshold value can subsequently be adjusted interactively.

Spearman's correlation converts a pair of markers' expression scores into ranks, and tests for correlation between the two sets of ranks. In this way, it detects monotonic relationships, that is, correlations where expression scores for the marker pair change consistently (i.e. increase or decrease), with respect to one another. Spearman's correlation is often more robust than Pearson's correlation, but picks up fewer classes of relationship than mutual information, which is a general measure of statistical dependence.

**Available for:** continuous and categorical scoring

## [Top]Viewing the results

See accessing and interpreting network results.

## [Top]Example output

**Figure 1:** An example protein network with edges representing significant Spearman correlation relationships