instructions on chi square

#1
I want to test before and after Likert scale data (4 points) for significance of change. From what I've read, t-test is problematic if I do the test more than once, so I am wondering if chi-square is the statistic I need. If so, can someone please suggest a page that offers clear but succinct instructions on how to carry out the chi-square test for significance on Likert scale data? Thanks.
 

JohnM

TS Contributor
#2
The same exact problems of doing multiple t-tests exist for doing multiple chi-square tests, which is an increasing probability of a Type I error (incorrectly asserting a difference when one doesn't exist).

If you do a chi-square, it's simply a test of goodness-of-fit. Check our post "Online Statistics Resources" in the Examples section.