+ Reply to Thread
Results 1 to 2 of 2

Thread: Repeated measures in a GLM, do I need to use a GLMM?

  1. #1
    Points: 11, Level: 1
    Level completed: 21%, Points required for next Level: 39

    Thanked 0 Times in 0 Posts

    Repeated measures in a GLM, do I need to use a GLMM?

    Hi guys,

    So I have finished an experiment where I had 11 cages of mice building nests with 3 different materials. Each cage was given a material and then observed for 30 minutes, with nesting behaviours counted and summed for each of the three individuals per cage. After 24 hours the nests were scored out of 5. This was repeated for each material.

    I've struggled trying to find the appropriate statistical test. The closest I've got to this is using a GLMM in spss, but I am struggling to understand what count as fixed/random factors etc.

    Any help would be greatly appreciated.



  2. #2
    Points: 3,882, Level: 39
    Level completed: 55%, Points required for next Level: 68

    Thanked 13 Times in 13 Posts

    Re: Repeated measures in a GLM, do I need to use a GLMM?

    Hi Daveinci,

    I don't quite follow the design. There were 3 mice per cage and 11 cages? Each cage was given 1 type of material so all 3 mice within a cage used the same material? Regardless, a general rule of thumb for determining what effect should be random is whether or not the effect is of particular interest to you. If you have no desire to make an inference about the effect then you can assume it to be a sample from a population of effects and therefore treat it as random. I would consider cage as a blocking effect and therefore random. Material would be a fixed effect.

    Hope this helps you on your way!

+ Reply to Thread


Posting Permissions

  • You may not post new threads
  • You may not post replies
  • You may not post attachments
  • You may not edit your posts

Advertise on Talk Stats