Constraining variances in asreml-R

From: zentree <asremlforum_at_VSNI.CO.UK>
Date: Tue, 24 Mar 2009 10:24:45 +0000

Hi,

I am comparing different methodologies for MET and in one of them I am running all the pairs of bivariate analyses for 70 sites, which means an awful lot of analyses. I wrote an R script that first run all the univariate analyses (fitting models appropriate for each site), stores the variance components and then I can use those components as starting values for the pairs.

My problem starts in that I would, sometimes, like to constraint one of the variances to a given value. For example, for some pairs I would like to constrain in4 to 0.01 (or something very small). Is there a simple way to fix in4 to 0.01?

Code:

dbh.bi <- asreml(cbind(dbh1,dbh2) ~ trait,
                         random = ~ Rep:diag(trait,init=c(in1,in2)) +
                         Rep:Sets:diag(trait,init=c(in3,in4)) +
                         Fem:corgh(trait,init=c(in5,in6,in7)),
                         data = cur,
                         rcov = ~ units:diag(trait,init=c(in8,in9)))

In plain vanilla ASReml I would use something like !GF. Can I do that in asreml-R without recurring to manually edit a starting values external file? Remember, I have to run this code over 2,000 times.

------------------------
Sacred cows make the best hamburgerÔ€”Mark Twain.

-------------------- m2f --------------------

Sent using Mail2Forum (http://www.mail2forum.com).

Read this topic online here:
http://www.vsni.co.uk/forum/viewtopic.php?p=433#433

-------------------- m2f --------------------
Received on Wed Mar 24 2009 - 10:24:45 EST

This webpage is part of the ASReml-l discussion list archives 2004-2010. More information on ASReml can be found at the VSN website. This discussion list is now deprecated - please use the VSN forum for discussion on ASReml. (These online archives were generated using the hypermail package.)