I would like to measure how similar the responses to the same survey are from two separate institutions. Would a correlation coefficient between two columns of mean scores for each question provide this information? Most of the questions are 5-point Likert scaled; the rest are rankings out of 4.

If a correlation coefficient could be meaningful, I infer from online reading that a Spearman's Rho might be appropriate due to the data being ordinal and discrete. Which t-Test would suit this - if any - for a measure of statistical significance?

Many thanks.


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.