hi, i have some data, a subset of which is pasted at the end of this message.
i am trying to understand how to do repeated measures as our study
design consists
of a subject and up to 2 siblings.
thus far, my model looks like this--with family_id indicating a
sibling relationship:
> formula = y ~ concordant + age.proband + age.other + sex.proband +
sex.other + Error(family_id)
i have seen a lot of resources where this is specified as
Error(family_id/(all_other_variables)),
should that be the case here? or is the above formulation sufficient
to capture the repeated
measures by famly?
also, there seem to be a number of resources for doing this type of
analysis, is a particular package that has more traction that i should
look into?
thanks,
-brent
concordant family_id external_ref.proband external_ref.other
sex.proband sex.other age.proband age.other y(fake)
T 58 80015550 80015543 M F 15 19 1
F 58 80015550 80016946 M F 15 8 2
T 54 80015499 80015338 F F 5 7 3
F 54 80015499 80013112 F M 5 13 4
F 22 80012269 80012252 F F 12 10 5
F 22 80012269 80018691 F M 12 8 5