Spearman's correlation coefficient when one variable is not normally distributed

Question: If you have two variables that one of them is normally distributed and the other is not normally distributed, should you use Spearman's rho for the correlation?

1 Answer

The question was answered here.

Short answer, it doesn't really matter. Both Spearman and Pearson's coefficients do not require normality. Spearman is more resistant to outliers though.

• thanks for the answer, but it's not consistent with the related literature. as i know bivariate normal distribution of data sets is one of the main underlying assumption to use pearson coefficient.!!!!!! – user81982 Jul 10 '15 at 19:18
• Hi @user81982, if you read the answer provided in the link I posted you'll find all the details you need. For example: "Pearson's correlation is a measure of the linear relationship between two continuous random variables. It does not assume normality although it does assume finite variances and finite covariance. When the variables are bivariate normal, Pearson's correlation provides a complete description of the association". – Edgar Derby Jul 12 '15 at 9:02