I'm using those data :
'data.frame': 1584 obs. of 3 variables:
$ Individual: Factor w/ 3 levels "AG201","AG202",..: 1 1 1 1 1 1 1 1 1 1 ...
$ Used : Factor w/ 2 levels "no","yes": 2 2 2 2 2 2 2 2 2 2 ...
$ NDVI : int 4724 4576 4894 4297 4670 4932 4346 3810 3481 4058 ...
I'm doing a glm with "NDVI" as a continuous explanatory variable, and then I'm plotting the model through the scatterplot of the data (I'm reproducing the same script as in the R book, Crawley, p.596)
model<-glm(Used~NDVI,binomial);
xv<-seq(0,10000,0.2);
yv<-predict(model,list(NDVI=xv),type="response");
plot(NDVI,Used);
lines(xv,yv);
My problem is that no line appears on my graph...
Any idea what's wrong?
Following Gavin's insight, here's a suggestion:
plot(NDVI, as.numeric(Used)-1 )
lines(xv,yv)
Factors are integer vectors starting at 1L
with assignments by default in alpha order of the labels. So you should be OK with "no" < "yes" leading to the No's being 1 and hte Yes's being 2 and then shifting down to the correct scale [0,1]. You may need to also look at str(yv)
The technical post webpages of this site follow the CC BY-SA 4.0 protocol. If you need to reprint, please indicate the site URL or the original address.Any question please contact:yoyou2525@163.com.