I'm confused by the wikipedia articles for fisher transformation for spearman and pearson. It looks like for pearson, the confidence interval is built around $\frac{1}{2}ln(\frac{1+\rho}{1-\rho})$ where $\rho$ is the true correlation coefficient, and for spearman it is built around $\rho=0$.

Is that the case? why? Isn't spearman simply applying the pearson correlation on ranks? Can both cases be specified in the same manner, e.g. building a confidence interval around the true spearman and the true pearson?

related to How to calculate a confidence interval for Spearman's rank correlation?



Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.