HLM or MLM

Go down

HLM or MLM

Post by CatieWalsh on Tue Mar 07, 2017 3:13 pm

Hi all! If you have been directed to this post, you stated that you were interested in, or are currently using, mixed models or hierarchical linear modeling in your analyses. Please use this forum to connect with each other either in person or online... It would be great if we could share knowledge and advice with each other!
avatar
CatieWalsh
Admin

Posts : 31
Reputation : 0
Location : OEH sometimes, but mostly wandering around Sennott

View user profile

Back to top Go down

Re: HLM or MLM

Post by mbowdring on Thu Jan 25, 2018 12:32 pm

Hi all,


Looking for some help regarding an analysis I'm running (any input would be appreciated!):

I'm working on examining factors impacting subjective intoxication scores among participants who received a placebo beverage in a lab-based alcohol administration study. I have 80 three-person drinking groups (240 participants total). Despite the slightly low number of groups, I had begun analyses using HLM to account for clustering within the three-person groups. However, upon inspection of the ICC I'm questioning whether HLM is even needed. The ICC is .055, which is very low and suggests to me that accounting for clustering may not be necessary. 

My two questions are:

1) Is there a standard ICC cutoff wherein multilevel modeling is deemed unnecessary? I can't seem to find one...

2) Would using a multilevel model when the ICC is sufficiently low have a negative impact on the results (i.e., somehow obscure them) or does the low ICC just mean that I could switch to a simpler (regression) model but don't necessarily have to?

Thanks!

- Molly
avatar
mbowdring

Posts : 3
Reputation : 0

View user profile

Back to top Go down

Back to top


 
Permissions in this forum:
You cannot reply to topics in this forum