[R] step() for glmmML

[Szentirmai Istvan]

Dear R Users,

I'm looking for a similar function as step() or drop1() for glmmML models,
but couldn't yet find any. I would appreciate if anyone could help me find
such a function.

Thanks,
Istvan


----- Original Message ----- 
From: <toby at abdn.ac.uk>
To: <r-help at stat.math.ethz.ch>
Sent: Monday, March 27, 2006 1:55 PM
Subject: [R] A plotting question - how to get error bars?


> Dear R list,
>
> Can anyone help with a plotting question? I'm trying to display some data
> on a plot and I've almost got the format I need (see code below), but 2
> things I can't get:
>
> 1. How to get "Jan","Feb","Mar" on the x=axis instead of 1:3?
> 2. How to get "T"s on the end of my error bars like you have in standard
> scientific plots?
>
> Any comments gratefully received!
>
> Thanks,
> Toby
>
> xvals=1:3 #couldn't get it to be "Jan, Feb, Mar" on the x-axis
> rgrT1=c(10,20,30)
> errbarsT1lo=c(0.5830952,0.3741657,0.8944272)
> errbarsT1up=errbarsT1lo
> rgrT2=c(25,30,35)
> errbarsT2lo=c(1.356466,3.535534,1.140175)
> errbarsT2up=errbarsT2lo
> minx=min(xvals);maxx=max(xvals)
> miny=min(rgrT1-errbarsT1lo,rgrT2-errbarsT2lo);maxy=max(rgrT1+errbarsT1up,rgrT2+errbarsT2up)
> plot(x=0,y=0,type="n",xlim=c(minx,maxx),ylim=c(miny,maxy),lab=c(2,20,0),bty="l",xlab="month",ylab="Relative
> Growth Rate")
> points(x=xvals,y=rgrT1,pch=21)
> symbols(x=xvals,y=rgrT1,boxplots=cbind(0,0,errbarsT1lo,errbarsT1up,0.5),inches=FALSE,add=TRUE)
> #symbols does the error bars, but without the "T"s at the end. The
> boxplot command does the Ts, but you can't have them without the box in
> the middle (and you can't have different symbols for points either)
> lines(x=xvals,y=rgrT1,lty=21)
> points(x=xvals,y=rgrT2,pch=24)
> symbols(x=xvals,y=rgrT2,boxplots=cbind(0,0,errbarsT2lo,errbarsT2up,0.5),inches=FALSE,add=TRUE)
> lines(x=xvals,y=rgrT2,lty=24)
> legend(x="right",c("Treatment 1","Treatment 2"),pch=c(21,24))
>
> ______________________________________________
> R-help at stat.math.ethz.ch mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! 
> http://www.R-project.org/posting-guide.html
>