0

I'm not here to kick up a fuss (I'm well aware of the fear of that whenever someone questions a decision to close or delete their answer) but I think maybe the "What constitutes original research" needs clarifying.

In an attempt to answer a question about a correlation I couldn't see any research done on it but the data was all there. I took the two data sets (with links to them) and compared them in a fairly trivial way (at least as far as I see it).

As it is original research is defined in the FAQ as when:

Answers are original research when they perform non-trivial analysis of available data and present a novel result which requires specialist expertise to review. It is acceptable to provide a collection of evidence, but not to apply non-trivial calculations that require a community of experts to evaluate. (This also includes the use of non-trivial Internet-based tools.)

In the comments it is said:

the general idea is "high-school level or lower" is trivial

Plotting two data sets against each other and calculating a correlation are high-school level.

Now I'm not saying my answer should have been kept, only that I had read the FAQ before posting my answer and hadn't thought it fell within original research.

  • 1
    Hi, I've removed the copy of the answer you pasted - the link works, but only for users that have access to deleted material. This is by design. Please avoid pasting deleted material here as we've had numerous problems in the past with users pasting answers to get around deletions. – Sklivvz Apr 26 '17 at 8:37
  • 2
    Not showing the material at issue means that no-one with less than 10k rep can participate in the Meta post. meta.stackoverflow.com/a/326226 – Josh Caswell May 5 '17 at 11:46
6

It seems the issue here is our definition of "trivial".

  • While each individual syllabus is going to differ by region, I do not think I was formally introduced to the formula for correlation co-efficients until my second year into a Maths degree. It wasn't addressed in high school.

  • You have chosen to only include the top 10 countries. You have not justified that choice. It doesn't seem reasonable.

  • You have chosen a formula for a linear correlation. You have not justified that choice.

  • You have little guidance for the reader to interpret the r value. Is -0.06 a strong negative correlation?

  • Your description of the p-value makes me uncomfortable.

To be clear, editing the answer to add more information to address these concerns won't help. It just demonstrates the analysis is non-trivial, and we have little reason to trust it. Instead, we should find expert analysis that has been peer-reviewed, and quote that.

You must log in to answer this question.

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