3 messages · Marte Lilleeng, Ben Bolker, John Fox
Hi everyone! I have a simple model that i would like to plot with 95% CIs. It is like follows: m1<-lmer(Richness~Grazing+I(Grazing^2)+(1|Plot),family=poisson) By using the effects package I get two plots, one for the linear term and one for the squared term. Q1: Can I get all in one? I.e. with one line for the whole model? Q2: Can I also visualize the random effects? I would be very happy for your answers!
Mvh Marte S. Lilleeng
Marte Lilleeng <mlilleeng <at> gmail.com> writes:
[snip]
I have a simple model that i would like to plot with 95% CIs. It is like follows: m1<-lmer(Richness~Grazing+I(Grazing^2)+(1|Plot),family=poisson) By using the effects package I get two plots, one for the linear term and one for the squared term. Q1: Can I get all in one? I.e. with one line for the whole model? Q2: Can I also visualize the random effects?
It would probably be best to send this to the r-sig-mixed-models list. You may want to look at the code at http://glmm.wikidot.com/faq for generating predictions and confidence intervals from lmer fits.
Dear Marte, On Thu, 25 Oct 2012 16:11:07 +0200
Hi everyone! I have a simple model that i would like to plot with 95% CIs. It is like follows: m1<-lmer(Richness~Grazing+I(Grazing^2)+(1|Plot),family=poisson) By using the effects package I get two plots, one for the linear term and one for the squared term. Q1: Can I get all in one? I.e. with one line for the whole model?
It's better to specify the model as Richness~poly(Grazing, 2)+(1|Plot) so that effect() understands that the quadratic is a single term in the model. Alternatively, I believe that Effect() would work as you want for either form.
Q2: Can I also visualize the random effects?
I'm not sure what that would mean. I suppose that you could look at the distribution of the BLUPs. I hope this helps, John ------------------------------------------------ John Fox Sen. William McMaster Prof. of Social Statistics Department of Sociology McMaster University Hamilton, Ontario, Canada http://socserv.mcmaster.ca/jfox/
I would be very happy for your answers! -- Mvh Marte S. Lilleeng
______________________________________________ R-help at r-project.org mailing list https://stat.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide http://www.R-project.org/posting-guide.html and provide commented, minimal, self-contained, reproducible code.