Linear Mixed Model for 3x2 repeated measures data

Moderators: statman, Analyst Techy, andris, Fierce, GerineL, Smash

Posts: 1
Joined: Wed Apr 25, 2012 9:52 pm

Linear Mixed Model for 3x2 repeated measures data

Postby RobertH » Wed Apr 25, 2012 10:12 pm

Hi all,

I'm trying to analyse some data from a study comparing alcoholic patients with matched control subjects. We measured the response time (RT) for participants to complete a memory task. They observed sequences that were 4, 5 or 6 items long, and had to repeat the sequence either immediately (0s) or after a delay (6s).

I would normally analyse the data using a rmANOVA examining the factors of sequence length (4, 5, 6) and timing (0, 6) for the two groups. Unfortunately there are many missing data points (some participants failed to get any correct responses in the delayed conditions), so I'd prefer to run a mixed model as I believe it can account for the missing data.

My SPSS sheet has columns labelled Participant, Group, Items, Delay and RT. I've tried taking some syntax from a website and adapting it, but I can't get it to run...

MIXED RT BY Participant Group Items Delay
/FIXED Group Items Delay
/RANDOM RT |Participant(Items*Delay) COVTYPE(ID)
/RANDOM RT |Participant(Items*Delay*Group) COVTYPE(ID)
/REPEATED SCHLYEAR | Participant(Items*Delay*Group) COVTYPE(AR1)

Essentially I'm interested in seeing the main effects of Items and Delay, whether there is an Item*Delay interaction, and whether any of these things interact with the group the participant is in.

Any help would be much appreciated!

Thanks in advance,

PS: In case it's of any relevance, I'm running this through SPSS 16.0.

Who is online

Users browsing this forum: No registered users and 3 guests