[R] Question about linear regression in R
R. Michael Weylandt
michael.weylandt at gmail.com
Tue Nov 15 06:11:48 CET 2011
What exactly is it that's worrying you? It's a problematic regression
for a few reasons, but ultimately it seems pretty ok, though I'd be
ever so slightly worried about the R^2 value being misinterpreted.
On Mon, Nov 14, 2011 at 10:49 PM, Miles Yang <miles2yang at gmail.com> wrote:
> Hi all,
> I wrote a r program as below:
> x <- 1:10
> y <- c(3,3,3,3,3,3,3,3,3,3)
> fit <- lm(log(y) ~ x)
> And I expect to get some error message from R, because "y" is constant.
> But, I got the message as below:
> lm(formula = log(y) ~ x)
> Min 1Q Median 3Q Max
> -6.802e-17 -3.933e-17 -1.063e-17 1.807e-17 1.530e-16
> Estimate Std. Error t value Pr(>|t|)
> (Intercept) 1.099e+00 4.569e-17 2.404e+16 <2e-16 ***
> x -1.275e-17 7.364e-18 -1.732e+00 0.122
> Signif. codes: 0 '***' 0.001 '**' 0.01 '*' 0.05 '.' 0.1 ' ' 1
> Residual standard error: 6.688e-17 on 8 degrees of freedom
> Multiple R-squared: 0.5794, Adjusted R-squared: 0.5269
> F-statistic: 11.02 on 1 and 8 DF, p-value: 0.01054
> How could this be possible?
> Did I missing something in my R code?
> Miles Yang
> E-mail：miles2yang at gmail.com
> [[alternative HTML version deleted]]
> R-help at r-project.org mailing list
> PLEASE do read the posting guide http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
More information about the R-help