Tell me more ×
Cross Validated is a question and answer site for statisticians, data analysts, data miners and data visualization experts. It's 100% free, no registration required.
up vote 3 down vote favorite

While most of the tests for normality help for continous variables, is there a way to test the normality assumptions for binary variables.

From what i've read on wiki, the K-S test can be applied for continous variables. How do we perform normality tests for binary (or even categorical variables)?

share|improve this question
3  
Since you have made a new question I think you should accept mbq's answer and link to your new question. – Andy W Oct 12 '10 at 13:19
vote to close. (but I'm below 500r) – M. Tibbits Oct 12 '10 at 13:47

1 Answer

up vote 10 down vote

There is no such thing as normality of categorical variable. Normal distribution is a continuous distribution so in assumption don't cover categorical output.

share|improve this answer
Ok, let me correct my question. How do you know if a binary variable follows the binomial distribution? – Roger Oct 12 '10 at 12:42
See en.wikipedia.org/wiki/Binomial_test . Talking as a moderator now: so can you please make a new, good question? You'll get a better answer and the wiki spirit of this site will be held. – mbq♦ Oct 12 '10 at 12:49
Sure. Let me do that. – Roger Oct 12 '10 at 13:14

Your Answer

 
discard

By posting your answer, you agree to the privacy policy and terms of service.