Programming the statistical procedures from SAS

How do I interpret type 3 tests of mixed effects? (with photo)

Accepted Solution Solved
Reply
Occasional Contributor
Posts: 12
Accepted Solution

How do I interpret type 3 tests of mixed effects? (with photo)

How do I interpret the following?

I know that because of the significant interaction, I shouldn't interpret lower order terms. 

What is the significant interaction telling me? And if it weren't significant, what would the lower order terms tell me? That there's a difference between groups?

New to SAS and kind of new to stats - I appreciate the help!

 

Untitled.png


Accepted Solutions
Solution
‎04-03-2018 10:35 AM
PROC Star
PROC Star
Posts: 404

Re: How do I interpret type 3 tests of mixed effects? (with photo)

The interaction indicates only that differences among the 3 DRUGs are not the same at all 7 TIMEHRs. It does not tell you anything about how or which means are different; you have to use post-hoc testing to sort that out. With a 3 x 7 factorial, the post-hoc testing is complex and (in my opinion) should be guided by the context of your study.

 

I would start by plotting the estimates of the interaction means. But then you'll need to learn a lot more about interpretation of ANOVA both with and without interaction. The topic is too complicated to address adequately in this Community forum. Good luck!

 

 

View solution in original post


All Replies
Solution
‎04-03-2018 10:35 AM
PROC Star
PROC Star
Posts: 404

Re: How do I interpret type 3 tests of mixed effects? (with photo)

The interaction indicates only that differences among the 3 DRUGs are not the same at all 7 TIMEHRs. It does not tell you anything about how or which means are different; you have to use post-hoc testing to sort that out. With a 3 x 7 factorial, the post-hoc testing is complex and (in my opinion) should be guided by the context of your study.

 

I would start by plotting the estimates of the interaction means. But then you'll need to learn a lot more about interpretation of ANOVA both with and without interaction. The topic is too complicated to address adequately in this Community forum. Good luck!

 

 

☑ This topic is solved.

Need further help from the community? Please ask a new question.

Discussion stats
  • 1 reply
  • 114 views
  • 0 likes
  • 2 in conversation