R help - Sep 2016 - R-square prob is not calculated by randomization in lmPerm::lmp

Any reason why the R-square prob is not calculated by randomization in
lmPerm::lmp? The help pages states "Either permutation test p-values
or the usual F-test p-values will be output", but I always get the F
test for R-square as with lm():

require(lmPerm)
x <- 1:1000
set.seed(1000)
y1 <- x*2+runif(1000,-100,100)
dat <- data.frame(x =x,y=y1)
summary(lmp(y~x, data=dat,center=FALSE,perm="Prob"))

[1] "Settings:  unique SS "

Call:
lmp(formula = y ~ x, data = dat, center = FALSE)

Residuals:
     Min       1Q   Median       3Q      Max
-100.431  -48.645    2.843   48.640  101.800

Coefficients:
  Estimate Iter Pr(Prob)
x    1.993 5000   <2e-16 ***
---
Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1

Residual standard error: 57.3 on 998 degrees of freedom
Multiple R-Squared: 0.9902, Adjusted R-squared: 0.9902
F-statistic: 1.009e+05 on 1 and 998 DF,  p-value: < 2.2e-16


-- 
Agustin Lobo
aloboaleu at gmail.com

That is contributed code. It could do anything the author felt like. I recommend
reading the source code.
-- 
Sent from my phone. Please excuse my brevity.

On September 5, 2016 11:52:15 PM PDT, Agustin Lobo <aloboaleu at
gmail.com> wrote:
>Any reason why the R-square prob is not calculated by randomization in
>lmPerm::lmp? The help pages states "Either permutation test p-values
>or the usual F-test p-values will be output", but I always get the F
>test for R-square as with lm():
>
>require(lmPerm)
>x <- 1:1000
>set.seed(1000)
>y1 <- x*2+runif(1000,-100,100)
>dat <- data.frame(x =x,y=y1)
>summary(lmp(y~x, data=dat,center=FALSE,perm="Prob"))
>
>[1] "Settings:  unique SS "
>
>Call:
>lmp(formula = y ~ x, data = dat, center = FALSE)
>
>Residuals:
>     Min       1Q   Median       3Q      Max
>-100.431  -48.645    2.843   48.640  101.800
>
>Coefficients:
>  Estimate Iter Pr(Prob)
>x    1.993 5000   <2e-16 ***
>---
>Signif. codes:  0 '***' 0.001 '**' 0.01 '*' 0.05
'.' 0.1 ' ' 1
>
>Residual standard error: 57.3 on 998 degrees of freedom
>Multiple R-Squared: 0.9902, Adjusted R-squared: 0.9902
>F-statistic: 1.009e+05 on 1 and 998 DF,  p-value: < 2.2e-16

For a linear model without an intercept term as in this example, neither
the usual permutation scheme for testing Ho: B1 = 0 nor usual definition of
R-squared apply.  So you need to check what the developer of this code
chose to do.  If I'm recalling correctly, in a linear model with an
intercept term the permutation test for Ho: B1 = B2 = ... Bp = 0 (i.e., all
coefficients other than the intercept = 0) is equivalent to a permutation
test for Ho: R-squared = 0.

Brian

Brian S. Cade, PhD

U. S. Geological Survey
Fort Collins Science Center
2150 Centre Ave., Bldg. C
Fort Collins, CO  80526-8818

email:  cadeb at usgs.gov <brian_cade at usgs.gov>
tel:  970 226-9326


On Tue, Sep 6, 2016 at 8:35 AM, Jeff Newmiller <jdnewmil at
dcn.davis.ca.us>
wrote:
> That is contributed code. It could do anything the author felt like. I
> recommend reading the source code.
> --
> Sent from my phone. Please excuse my brevity.
>
> On September 5, 2016 11:52:15 PM PDT, Agustin Lobo <aloboaleu at
gmail.com>
> wrote:
> >Any reason why the R-square prob is not calculated by randomization in
> >lmPerm::lmp? The help pages states "Either permutation test
p-values
> >or the usual F-test p-values will be output", but I always get the
F
> >test for R-square as with lm():
> >
> >require(lmPerm)
> >x <- 1:1000
> >set.seed(1000)
> >y1 <- x*2+runif(1000,-100,100)
> >dat <- data.frame(x =x,y=y1)
> >summary(lmp(y~x, data=dat,center=FALSE,perm="Prob"))
> >
> >[1] "Settings:  unique SS "
> >
> >Call:
> >lmp(formula = y ~ x, data = dat, center = FALSE)
> >
> >Residuals:
> >     Min       1Q   Median       3Q      Max
> >-100.431  -48.645    2.843   48.640  101.800
> >
> >Coefficients:
> >  Estimate Iter Pr(Prob)
> >x    1.993 5000   <2e-16 ***
> >---
> >Signif. codes:  0 '***' 0.001 '**' 0.01 '*'
0.05 '.' 0.1 ' ' 1
> >
> >Residual standard error: 57.3 on 998 degrees of freedom
> >Multiple R-Squared: 0.9902, Adjusted R-squared: 0.9902
> >F-statistic: 1.009e+05 on 1 and 998 DF,  p-value: < 2.2e-16
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> 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.
>
>
	[[alternative HTML version deleted]]