An embedded and charset-unspecified text was scrubbed... Name: not available URL: <https://stat.ethz.ch/pipermail/r-sig-mixed-models/attachments/20110616/cb8e18fc/attachment.pl>
Heteroscedastic error model
2 messages · GRIGNOLA, FERNANDO E [AG/1000], David Duffy
On Thu, 16 Jun 2011, GRIGNOLA, FERNANDO E [AG/1000] wrote:
I've done quite a bit of search and have not been able to find information on how to fit a model with heteroscedastic error variances. For example, I would like to fit a simple model with genotypes crossclassified across locations and heterogeneous residual variances. It looks like the functionality was there in lme but not anymore in lmer. Are there any workarounds or new packages (lme4a, Bayesian, ...) that can do this type of analyses?
Perhaps I misunderstand, but can't one get this model by adding appropriate random effects interaction terms? Cheers, David Duffy.
| David Duffy (MBBS PhD) ,-_|\ | email: davidD at qimr.edu.au ph: INT+61+7+3362-0217 fax: -0101 / * | Epidemiology Unit, Queensland Institute of Medical Research \_,-._/ | 300 Herston Rd, Brisbane, Queensland 4029, Australia GPG 4D0B994A v