Re: [R] formula

From: Adaikalavan Ramasamy <ramasamy_at_cancer.org.uk>
Date: Fri 16 Jul 2004 - 02:06:07 EST

If you want to fit "y = a + bx", then you use "lm(y ~ x)" instead of "lm(y ~ A + bx)". 'A' is not a parameter but coefficient and you do not need to specify coefficients, which is what the linear model is trying to do anyway ! See the details section of help("formula").

> x <- 1:5
> y <- c(0, 1.0, 1.7, 2.0, 2.1)
> lm(x ~ y)

Call:
lm(formula = x ~ y)

Coefficients:

(Intercept)            y
     0.6828       1.7038

If A was already defined, and you are trying to multiply the y-values, then use the I() operator. This protects the term/calculation and inhibits the usual term interpretation in linear models.

> lm(x ~ I(2*y) )

Call:
lm(formula = x ~ I(2 * y))

Coefficients:

(Intercept)     I(2 * y)
     0.6828       0.8519

PS : I think there is a typo in the y input as there is no such number as 2.1.4

On Thu, 2004-07-15 at 16:28, solares@unsl.edu.ar wrote:
> Hi, i 'dont understand how to take a general formula, view this:
>
> x<-1:5
> y<-c(0,1,1.7,2,2.1.4)
> dummy<-data.frame(x=x,y=y)
> formula<-"y~A*log(x)/log(2)"
> formu<-as.formula(formula)
> fm<-lm(formu,data=dummy)
> Error in eval(expr, envir, enclos) : Object "A" not found
>
> but A is the parameter of fitting, why is this?Thanks Ruben
>
> ______________________________________________
> R-help@stat.math.ethz.ch mailing list
> https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html
>



R-help@stat.math.ethz.ch mailing list
https://www.stat.math.ethz.ch/mailman/listinfo/r-help PLEASE do read the posting guide! http://www.R-project.org/posting-guide.html Received on Fri Jul 16 02:29:01 2004

This archive was generated by hypermail 2.1.8 : Wed 03 Nov 2004 - 22:54:59 EST