I just discovered this site, and I had a question that has been bugging me for a while. My question isn't so much about a concept as it is about terminology, so I thought I'd check whether this kind of question is acceptable on the site before I ask it.

As an example, here is the question I intended to ask:

My statistics professor claims that the word "correlation" applies strictly to linear relationships between variates, whereas the word "association" applies broadly to any type of relationship. In other words, he claims the term "non-linear correlation" is an oxymoron.

From what I can make of this section in the Wikipedia article on "Correlation and dependence", the Pearson correlation coefficient describes the degree of "linearity" in the relationship between two variates. This suggests that the term "correlation" does in fact apply exclusively to linear relationships.

On the other hand, a quick Google search for "non-linear correlation" turns up a number of published papers that use the term.

Is my professor correct, or is "correlation" simply a synonym of "association"?


I don't see any problem with your asking that question. Note that we have a tag for terminology () with 81 so categorized questions to date (2/4/13).

I do think that terminology can be somewhat fuzzy and frustrating, with different people using the same term to mean different things, or different terms to mean the same thing. It is possible that a terminological question thus has no real 'right' answer. If this troubles people, they may ask to have your question made community wiki, which is a status where you don't get any reputation for upvotes. I could imagine that you might find this annoying, but it certainly wouldn't impact your ability to ask the question and get an answer. (For the record, I don't think your question should have to be made CW, I'm just grasping for any possible complication.) Other than that, I can't imagine any issues at all.

  • $\begingroup$ Thanks gung; I wouldn't mind the question being CW'd, so long as it has a chance of being answered. $\endgroup$ – Asad Saeeduddin Feb 5 '13 at 3:43

While I am obviously very much non-senior, I don't see why there can't be some questions about terminology. Statistical terminology is very important within the community of practice for statistics (try publishing a paper using the wrong terms for your audience, you'll likely get some nasty comments).

Worse, different related communities of practice use the same terms for different things. Statisticians, computer scientists, physicists, and social scientists all use a solid amount of stats. They do not always use the same terms for the same concepts, which is complicated significantly by the fact that AI and CS is heavily Bayesian while social science is heavily frequentist.

If anything, I'd think there might need to be some guidelines for answering such questions. I don't think any answer about terminology is remotely useful unless it cites a source and states the domain of science where such terminology is used.


You must log in to answer this question.

Not the answer you're looking for? Browse other questions tagged .