Message-ID: <20141127120442.20791bfma54oejq0@www.staffmail.ed.ac.uk>
Date: 2014-11-27T12:04:42Z
From: Jarrod Hadfield
Subject: interpretation variance-covariance estimates with gaussian and censored exponential
In-Reply-To: <B4D4B84E4C26984690619D21577874EAA6240C16@xmail33.ad.ua.ac.be>
Hi,
The linear model is applied on the same link scale for both fixed and
random effects so it will be hazards also.
Cheers,
Jarrod
Quoting Van Dongen Stefan <stefan.vandongen at uantwerpen.be> on Thu, 27
Nov 2014 10:45:09 +0000:
> Hi All,
>
> I am currently running a multivariate animal model which has 3
> normally distributed responses and one time-to-event (longevity)
> response. For the fixed effects part, the estimated slopes for
> associations with longevity reflects changes or ratio's in hazards
> (i.e., positive estimate = shorter longevity), but how should I
> interpret the covariances/correlations in the variance covariance
> matrices (genetic and environmental)? Correlations with hazards or
> survival-times?
>
> many thanks
>
> Stefan
>
> -------------------------------------------------------------------------------------------------------------------------
> Prof. Dr. Stefan Van Dongen
> Evolutionary Ecology - Department of Biology - University of Antwerp
> (http://www.ua.ac.be/eveco)
> StatUA Statistics Center, University of Antwerp (http://www.ua.ac.be/statua)
> Groenenborgerlaan 171 - B-2020 Antwerp - Belgium
>
> room V324b, building V, campus Groenenborger
> Tel: + 32 3 265 33 36
> Fax: + 32 3 265 34 74
> http://www.ua.ac.be/stefan.vandongen
> --------------------------------------------------------------------------------------------------------------------------
>
>
> [[alternative HTML version deleted]]
>
> _______________________________________________
> R-sig-mixed-models at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-sig-mixed-models
>
>
--
The University of Edinburgh is a charitable body, registered in
Scotland, with registration number SC005336.