Unless you are doing hypothesis tests normality doesn't matter. It might be helpful if you said what questions your analysis was meant to answer and give some details about your variables. That is often how you choose correlation methods. Best, David Booth

Dear Catarina,

Pearson correlation measures the strength of the linear relationship between normally distributed variables. In contrast, if the variables are not normally distributed or the relationship between the variables is not linear, Spearman method would be more appropriate to use.

If you could have a look at this paper, it explains well the difference between Spearman and Pearson methods

" COMPARISON OF VALUES OF PEARSON’S AND SPEARMAN’S

CORRELATION COEFFICIENTS ON THE SAME SETS OF DATA"

By Jan Hauke, Tomasz Kossowski

Dear Catarina,

Spearman method would be more appropriate to use.

Mohammed

In the case of not normally distributed data I would suggest to use the Spearman's rho correlation coefficient.