TutorTermTell Us What Is StuckGet in Touch

My data is not normal. What do I do?

Check how far from normal and with what sample size, because many tests are fairly robust to moderate deviation at larger samples. Then choose deliberately between a non-parametric alternative, a transformation and a robust method, and report the choice. The problem is never non-normality itself, it is non-normality that goes unmentioned.

This comes up on Choosing the Right Statistical Test, where it is answered in the context of the work itself.

Get My Free QuoteBrowse all questions

More on data analysis

See all
My data is not normally distributed. Is the analysis ruined?My ethics board wants a sample size justification. What do they need?My frame changed halfway through. Have I ruined it?My output does not look like the examples in my textbook.My project is already a mess. Can it be fixed?My results contradict my hypothesis. Is that bad?My two strands disagree. What do I do?Parametric or non-parametric?Should I code on paper first?What about mixed methods?What does it mean when Levene's test is significant?What goes in results and what goes in discussion?What is a good effect size to assume?What is a joint display?What is G*Power?What is saturation and how do I show I reached it?What is the difference between a code, a category and a theme?What makes a study mixed methods rather than just having two datasets?What test do I use for Likert scale data?Which design should I use?
Not what you asked?

Ask us the actual question

Send the draft, the rubric or the score report with it. You get a real answer and a price before you commit to anything.

Get My Free Quote[email protected]