Issues with Binomial variables, missing values & workspace

From: tschrades <asremlforum_at_VSNI.CO.UK>
Date: Thu, 20 Aug 2009 15:02:53 +0100


I am a graduate student from the University of North Dakota and I have been working with a complex pedigree to study the influences of temperature on sex and would like to use ASReml for my analysis. I have read the user manual, but I am still having some difficulties. I took a subset of my pedigree to make it easier to start using the program. I trying to fit an animal model for my analysis, but I have a binomial dependent variable (Sex, coded 0 and 1) and missing data in the pedigree. I don't want to include the missing values, but if I don't include !MVINCLUDE the analysis fails. I tried using the !DV* that was recommended to another person, but I haven't gotten that to work either. I also can't get the !BIN !LOGIT qualifiers to work, so the software treats my dependent variable like a binomial variable and not a continuous variable. Also, for my large pedigree file, I get a pedigree too big or in error and I tried the !WORKSPACE 500 qualifier, but it didn't seem !
 to help either. If anyone could provide some insight into these problem, I would really appreciate it. I have included my basic model below.



Example Analysis
Sex !DV
Example.csv !MAXIT 100 !EXTRA 20 !MVREMOVE !SKIP 1
Sex !BIN !LOGIT ~ mu Temp !r ID

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

Sent using Mail2Forum (

Read this topic online here:

-------------------- m2f --------------------
Received on Fri Aug 20 2009 - 15:02:53 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.)