Hello,
I observed ant colony formation under different conditions. Every week I counted the number of eggs, number of larvae, number of pupae and number of workers untile the colony reach a set number of workers. I have 3 types of condition for which I have replicates (colony ID). As the number of each variable I measured can be influenced by the number of the others, I want to do a multivariate GLMM with the four dependent variables. However, I do not find how to do it using GLIMMIX. Is it possible?
the data are like
colony_ID condition week egg_ng larvae_nb pupae_nb worker_nb
1 A 1 0 0 0 0
1 A 2 2 0 0 0
1 A 3 3 1 0 0
2 A 1 0 0 0 0
2 A 2 4 3 0 0
.
.
.
70 C 62 10 15 12 8
Thanks for your help.
Here is an example of GLIMMIX fitting a model to bivariate responses, but I'm not sure if this works in your case as it seems that the two responses need to have different distributions. But you can try it out.
Thank you but i do not see the example. Would it work woth more than two dependent variables?
I left out the link. My apologies.
Here is the link: https://documentation.sas.com/doc/en/pgmsascdc/9.4_3.4/statug/statug_glimmix_examples08.htm
Will it work for more than 2 dependent variables? I leave that up to you to figure out by trying it.
Nevertheless, as I said if your variables all have the same distribution (for example, all normally distributed), I don't think this example applies and I don't think GLIMMIX handles this.
Thank you for the link. I found the same thing yesterday while looking how to do it and I don't think it works for what I want to do.
Thank you for your help.
It's finally time to hack! Remember to visit the SAS Hacker's Hub regularly for news and updates.
Learn how use the CAT functions in SAS to join values from multiple variables into a single value.
Find more tutorials on the SAS Users YouTube channel.
Ready to level-up your skills? Choose your own adventure.