Calculate parameter estimate for reference level

[szm]

Hello all,

I fit a complicated model in proc glimmix with 2 categorical variables (6 and 8 levels respectively) and the linear and quadratic form of a continuous variable with all interactions.
The 3-way interaction is significant and I want to isolate the regression models for each combination of the two categorical variables and calculate the maxima (derivative of quadratic function for each combination).
My problem is that there are many levels of categorical variables and I find it difficult to correctly estimate all parameter estimates.

Is there a way to get the actual parameter estimates without having to manually calculate them? Or is there an example of something as complicated so I can learn how to do it?

Thanks

 

[noetsi]

Couldn't you write a Contrast statement to do this? I don't do this type of statistics, and don't use glimnix as a result, but I would look at these statements and see if they help.

 

[hlsmith]

I'll pull things back a ways. 3-way interactions are pretty much non-existent. And looking at a crap ton of them is going to find a spurious one. This would also require lots and lots of data to power. And well, while you have all this data,why don't you create a data split. Look for these unicorns in the first split. Once you find them see if they exist in the second split.