repeated measures
[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

repeated measures

I am new to asreml so sorry if this is repetitive.

I am working through the Wolfinger rat data p121-124 of the manual. The CS
and AR(1) examples are fine.

Now  for  RCL I do not get the log L as given in table 8.1 p 124. My
understanding is that we are fitting random terms of b1+b2*t where t
represents time of measurement (=1,2,3,4,5 obtained from lin(Trait)). So
the var-cov structure of b1,b2 is specified in the variance structure "2 O
US 5 -1.6 1.3". The output from this run only gives two variance components
(other than random error) and if you replace the variance structure with a
diagonal matrix "2 0 DIAG 5 1.3" you get the same result. So where has the
covariance between b1 and b2 gone ? Or what am I doing wrong.

I have also tried to change the fixed model to include a linear trend on
time but it doesn't like removal of "Trait" or its replacement by "mu". I
just get "..error in model factor list".

Are there any other annotated examples of repeated measures data ?

Any help appreciated.
Dave Johnson.