Dear List, Consider the following example x=c(1,2,3,4,5) y=c(2,4,6,8,10) linearmodel=lm(y~x) To predict a y-value if you know the corresponding x value is very easy with the command predict. predict(linearmodel, newdata=(x=1.5)) The other way around, to predict an x-value with a corresponding y-value, doesn't work unfortunately. Is there another function that can do that, or do I need to solve that problem the classical way? Thanks in advance Gerrit Voigt
predict function the other way around
2 messages · Gerrit Voigt, David Winsemius
Why not use the x=T and y=T paramemters and see if :
linearmodel=lm(y~x, x=T, y=T)linearmodel$model
(linearmodel$model)
y x
1 2 1
2 4 2
3 6 3
4 8 4
5 10 5
.... give you useful results. If you want to interpolate or
extrapolate, then search for threads regarding those tasks.
David Winsemius On May 11, 2009, at 11:20 AM, Gerrit Voigt wrote: > Dear List, > Consider the following example > > x=c(1,2,3,4,5) > y=c(2,4,6,8,10) > linearmodel=lm(y~x) > > To predict a y-value if you know the corresponding x value is very > easy with the command predict. > > predict(linearmodel, newdata=(x=1.5)) > > The other way around, to predict an x-value with a corresponding y- > value, doesn't work unfortunately. > Is there another function that can do that, or do I need to solve > that problem the classical way? > > Thanks in advance > > Gerrit Voigt > > ______________________________________________ > 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. David Winsemius, MD Heritage Laboratories West Hartford, CT