Hello all,
I found the following code worked.
code
require(boot)
function.fit2 <- function(data,i){
d <- data[i,] # select obs. in bootstrap sample
fit2 <-lm(logDIS~logBMN+I(logBMN^2), data=dataN)
coefficients(fit2) # return coefficient vector
}
boot.fit2 <- boot(dataN, function.fit2, 1000)
On Mon, May 6, 2013 at 7:36 AM, Elaine Kuo <elaine.kuo...@gmail.com> wrote:
> Hello,
>
> I want to know if two quadratic regressions are significantly different.
> I was advised to make the test using
> step 1 bootstrapping both quadratic regressions and get their slope
> coefficients.
> (Let's call the slope coefficient *â*^1 and *â*^2)
> step 2 use the slope difference *â*^1-*â*^2 and bootstrap the slope
> coefficent
> step 3 find out the sampling distribution above and calculate the % =0
> step 4 multiple the % by 2
>
> However, I am new to the package boot.
> I wrote a code for step 1 and got a error message.
>
> Please kindly advise how to modify it and thank you.
>
> Elaine
>
> code
> require(boot)
> function.fit2 <- function(data){
> #data <- data[indices,] # select obs. in bootstrap
> sample
> fit2 <-lm(logDIS~logBMN+I(logBMN^2))
> coefficients(fit2) # return coefficient vector
> }
>
> boot.fit2 <- boot(dataN, function.fit2, 1000)
>
> error
> > fit2.boot <- boot(dataN, fun.fit2, 1000)
> Error in statistic(data, original, ...) : unused argument (original)
>
>
[[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.
