I have a dataset based upon observation from related individuals. I have a kinship matrix that estimates the pairwise relationship between every two individuals in the sample. My question is, how do I specify that matrix in a variance component model?
My best guess is PROC GLIMMIX. I understand how to specify the STRUCTURE of a covariance matrix, but that's not what I want to do. I already have the covariance matrix calculated, now I need to use it in a model.
Try Googling "+pedigree +covariance +matrix +proc +mixed" (without the quotes). The first hit should be "Genetic analysis of complex traits using SAS - Google Books Result". If you click on that, you can see a couple of pages of text in which the INBREED procedure is used to construct a kinship matrix. The kinship matrix is then passed to the MIXED procedure.
I would suggest that you purchase the book so that you can get the most from it. It looks like it could be quite useful
Thanks Dale, that is very helpful. I have another related question:
I used PROC INBREED to construct the kinship matrix. Unfortunately I have a very large pedigree, which makes the matrix unwieldy. In reality I only need the kinship coefficient estimated for a small sample of pairwise relationships in the pedigree.
For example, I have observations on N individuals, who are connected via a single pedigree which contains Y individuals. Y >> N.
Can I tell PROC INBREED to use all Y individuals to estimate the kinship coefficients between only the N observed individuals?