rudeboybert
commented
4 years ago Hi @oscci, we decided to not include CI's in our get_correlation() function. Much as it is incumbent on individuals who use stats:cor() to know that if their input represents a sample then there is uncertainty, so also will this be the case with our get_correlation() function. In particular since get_correlation() is merely a wrapper to stats:cor().
At this point we feel the additional complexity of both implementing this and adding to output complexity is not merited. Thanks for your suggestion none the less.
@oscci: For some reason, perhaps historical, it is unusual for people to include 95% CI with correlations. Instead they just discuss whether 'significant' or not. If the get_correlation function automatically gave you the 95% CI, it would help educate people to stop interpreting correlation coefficients as precise estimates, particularly with small N.
@rudeboybert: It is very true people often misinterpret sample correlation with population correlation. We'll keep your suggestion in mind when we get around to improving
get_correlation(), as there are a host of other improvements needed #29 #32 #38