Strange GLMM Output

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

pbertoli
Posts: 1
Joined: Wed Dec 07, 2016 12:02 pm

Strange GLMM Output

Postby pbertoli » Wed Dec 07, 2016 12:40 pm

Hi guys,

I'm having little problems with my GLMM analyses in SPSS.
I have behavioural data of black-lion-tamarins in captivity. I have 11 individuals that I observed for 30 days twice a day (morning and affternoon).
So my data is like this
Individual Sex Day Period Season Type of cage Group size Agonism Vigilance Behavious potentially indicative of stress Inactive (...)
M1 male 05jan morning summer big Group 0 0,3 0,1 0,1 (...)
.
.
.
For the Behavioral categoris I have the relative frequency of each category per day per period. So, I have the same measure 2 times for individual per day, totalizing 60 measures per individual (11 individuals x 60 measures = 660 )
I want to know if the group size and the type of cage influence the behavioral categories. So in my model I put individual as a subject, day and period as a repetitive measure. The behavioral categorie as a response variable(target), and group size/ type of cage/period/season as a predictive variable.

My output was very strange
Data structure: a table with only one individual with only one period, and with the target. I couldn't paste the table here.

Residual effect: a huge table with the residual effect (Var=period=morning/day=05jan or affternoon/day=05jan), estimate, std. Error, Z, sig, 95% confidence interval.

I don't know if my model is correct, and if it is, I don't know how to interpret this output.
Someone can help me?
If you can't understand something let me know. I can send the output to any of you by email.

Thanks a lot
statman
Administrator
Posts: 2723
Joined: Tue Jun 12, 2007 12:08 pm
Location: Florida, USA

Re: Strange GLMM Output

Postby statman » Wed Dec 07, 2016 3:13 pm

Please ...............
See the note below

NOTE: Please read the Posting Guidelines and always tell us your OS, the SPSS version and information about your study and data!

Statman
Statistical Services

Who is online

Users browsing this forum: No registered users and 2 guests

cron