Hey,
I'm stuck on something I already did before (just a different kind of
database), and whatever I try, it doesn't work anymore. So thanks for your
help.
Here's how my data approximately looks like:
year season replicate size freq weight
2000 summer ch1 6 1 45
2000 summer ch1 6.5 12 46
2000 summer ch1 7 33 470
I have 2 years (2000 and 2001) and 2 seizons (winter and summer). I wanted
to plot weight~size, with 2 groups (year and seizon), so here's my shortened
script for that:
database$groups=paste(database$seizon,database2$year,sep=" ")
xyplot(database$weight~database2$size,
groups=database$groups,
par.settings=list(superpose.symbol=list(col=col.list,pch=c(21,16,21,16))),
auto.key=list(corner=c(0.1,0.9),lines=F,points=T))
Which works fine, the problem comes when I try to add 2 exponential curves
to the data (the 2 seizons). I tried this:
summ=subset(database,seizon=="summer")
modsumm=nls(summ$weight~exp(a+b*summ$size), data=summ, start=list(a=0,b=0))
exposumm=curve(exp(0.05354+0.19872*x), from=0, to=22, add=T, lwd=1,
col="blue",lty=1)
After having to add plot.new() in the front, the line does or not show up,
or shows up but wrongly placed. I thought this might be because of the
subset, so I wanted to do something like this:
modsumm=nls(weight~exp(a+b* size), data=engsAGG2[seizon=="summer"],
start=list(a=0,b=0))
which returns: "undefined columns selected"
Thanks in advance for the reply.
[[alternative HTML version deleted]]
______________________________________________
R-help@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.
