NOW LIVE! Today's the day you meet your new best friend. You don’t have to leave Wolfy behind... In 'Pets & Sidekicks' your companions level up with you!

Reply to thread

Message: <blockquote data-quote="cmbarona" data-source="post: 4981081" data-attributes="member: 71281">Well... While Snoweel is on hiatus, I should quickly attempt to clarify the analytical point he was trying to make.Correlations do not imply causation.BUT, in the world of statistical analysis, it is assumed that a strong enough correlation still has SOME underlying cause.Let's assume for a moment that there is a correlation between two variables:Variable A: Bad DMingVariable B: the darkness/grimness/grittiness of a worldLet's further assume that this correlation is positive (when one variable increases, the other variable increases).If this is true, it is assumed that one of three possibilities exist:1) Variable A causes Variable B2) Variable B causes Variable A3) Some third, unknown variable is the cause of the correlation between A and BThat's all that was meant when he said there has to be some underlying cause.However, I believe he made a separate point assuming that option 2 is in some way true. Someone please correct me if I misinterpreted his post, or if I am wrong in my recollection. But this new argument (option 2 is correct) is distinct from the point he was making about statistical analysis (one of the three options must be correct).All that being said, first, I disagree with his correlation, and second, he really should know better than to postulate conclusions on a correlation that has no evidence for its existence. Perhaps he was just hypothesizing, but hypotheses usually come before a study, and can only be (usefully) discussed after those results are in. They are not valid points of argumentation in and of themselves.P.S.: I'll take one step farther and point out that correlations still have some degree of predictive value. One can look at a correlation and say that, if one variable increases, chances are, the other variable will increase. However, attempting to explain that increase without further study is usually unhelpful.</blockquote>

Verification