On 04.10.2011 13:30, Peter Minting wrote:>
> Dear R-help
> Can anyone tell me why my curve appears the wrong way round on a rug plot?
> I am using the same code as on pg 596 of the Crawley R-book.
> mod<-glm(mort~logBd,binomial)
What is mort, what is logBd? I don't have access to the book. I have
hidden it in my other office so that nobody can find it anymore.
> par(mfrow=c(2,2))
> xv<-seq(0,8,0.01)
> yv<-predict(mod,list(logBd=xv),type="response")
> plot(logBd,mort)
> lines(xv,yv)
> I've tried swapping xv and yv around but no luck.
Hopefully mort is a binary factor, i.e. with two levels. I that case
they are at positions 1 and 2 on the y axis in plot().
yv is the reponse, i.e. is in the interval (0,1) if the binomial glm was
successful. So a different scale.
So I guess
lines(xv,yv+1)
could help.
Whatelse I think about "The R Book" can be found in my book review
published in "Statistical Papers".
Best,
Uwe Ligges
> Thanks,
> Pete
> [[alternative HTML version deleted]]
>
> ______________________________________________
> 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.