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 1 down vote favorite

Can you still used the least significant difference test even if the F test is not significant?

share|improve this question
An F-test of what? If an ANOVA, how many levels, variables, interactions etc? If it's just two levels they don't report anything different. – John Oct 12 '11 at 16:42

1 Answer

up vote 1 down vote

It depends on what you mean. If you want to graph your data and use LSDs to indicate that things were not significant in the tests, and also demonstrate the range of values you could have found significant for a particular comparison then go right ahead.

If you want to go on a fishing expedition within your data then be advised your chances of finding making a Type I error will be substantially greater than alpha.

share|improve this answer
John its for multiple linear regression (levels of categorical variable). Im supposed to get a significant F (but I am not). Maybe because the reference group is wrong? – Tom Oct 12 '11 at 16:51
@Tom It is Q&A not a forum, so please use comments for comments. Moreover I see you lost your account -- I have fixed that, but please register here: stats.stackexchange.com/users/login . – mbq♦ Oct 12 '11 at 17:14
1  
Add more to your question, edit it until it better reflects your problem, what you've tried, and things like your guess about the reference group. – John Oct 12 '11 at 19:11

Your Answer

 
discard

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

Not the answer you're looking for? Browse other questions tagged or ask your own question.