Programming the statistical procedures from SAS

How do I nest 3 random effects in Proc Mixed?

Reply
Regular Learner
Posts: 1

How do I nest 3 random effects in Proc Mixed?

I'm looking for some help nesting factors.

 

I have the following experiment design:

 

Four Treatments

Four pens per treatment

Four sampled animals per pen

3 samples measured per animal, sometimes just two samples measured, at the same time point.

 

Previously, I have only take one sample per animal, and my mode and random statement with nesting looks something like

 

Model = Treatment / cl;

Random Pen(Treatment);

 

I'm wondering how I could work Animal into that statement.  Maybe Animal*Pen(Treatment), or Animal (Pen Treatment) ?

 

Furthermore, when I write out a linear model equation, I would represent the Pen(Treatment) as uij

 

u for random effect of j pen for i treatment

 

How would I properly state it if I incorporated Animal?

 

uija, with a for animal maybe?

 

I look forward to any thoughts on this would be appreciated.  Apologies if my stats language is a bit imprecise.  Too much veterinary medicine and not enough math in my life.

PROC Star
PROC Star
Posts: 188

Re: How do I nest 3 random effects in Proc Mixed?

[ Edited ]

Assuming that treatment is the only fixed effect:

class treatment pen animal;
model y = treatment; random pen(treatment)   animal*pen(treatment);

Given how SAS expands syntax, there are equivalent ways to identify a random effect in this model:

"pen(treatment)" == "pen*treatment"

"animal*pen(treatment)" == "animal*pen*treatment" == "animal(pen treatment)"

 

Equation-wise, something like (without going to the trouble of proper symbols)

 

y_ijkm = mu + t_i + p_ij + a_k(ij) + e_m(ijk)

 

where i indexes treatment t

j indexes pen p

k indexes animal a

m indexes sample e (residual error)

 

Ask a Question
Discussion stats
  • 1 reply
  • 145 views
  • 0 likes
  • 2 in conversation