Spearman correlation coefficient

This is the most commonly used non-parametric correlation coefficient in our field. It is simply the Pearson correlation coefficient between the ranks of the scores on the two variables.

Spearman coefficients are often given the Greek letter rho where Pearson correlation coefficients are usually denoted by R.

Details #

The above about the Spearman correlation being a Pearson correlation of ranks is true when there are no ties among the scores on either variable, things are a bit more complicated when, as there often are for OM data, ties in the data. However, this is getting a bit beyond the level we need outside rather academically pedantic research publications!

Try also … #

Pearson correlation coefficient
Kendall correlation coefficient

Chapters #

Not specifically mentioned in any of the chapters.

Online applications #

I have (at last) created a shiny app you can use to find the confidence interval around any Spearman correlation coefficient given the n.
At some point I hope to add another shiny app into which you can upload data and get the scattergram for the data and correlation coefficients with the confidence interval around that observed value.

Dates #

Tweaked to add link to shiny app 27.xi.23.

Powered by BetterDocs