[R] Loop with string variable AND customizable "summary" output
Marc Schwartz
marc_schwartz at comcast.net
Mon Jan 29 21:01:03 CET 2007
On Mon, 2007-01-29 at 14:30 -0500, Gabor Grothendieck wrote:
> Note that the nlme solution seems to give the same coefficients
> but appears to use a single error term rather than one error
> term per level of the conditioning variable and that would change various
> other statistics relative to the other solutions should that matter.
>
> > summary(lmList(uptake ~ conc | Treatment, CO2))
> Call:
> Model: uptake ~ conc | Treatment
> Data: CO2
>
> Coefficients:
> (Intercept)
> Estimate Std. Error t value Pr(>|t|)
> nonchilled 22.01916 2.46416 8.935769 1.174616e-13
> chilled 16.98142 2.46416 6.891361 1.146556e-09
> conc
> Estimate Std. Error t value Pr(>|t|)
> nonchilled 0.01982458 0.004692544 4.224699 6.292679e-05
> chilled 0.01563659 0.004692544 3.332221 1.306259e-03
>
> Residual standard error: 8.945667 on 80 degrees of freedom
<snip>
Gabor,
Thanks for noting that. There is a solution using 'pool = FALSE':
> summary(lmList(uptake ~ conc | Treatment, CO2, pool = FALSE))
Call:
Model: uptake ~ conc | Treatment
Data: CO2
Coefficients:
(Intercept)
Estimate Std. Error t value Pr(>|t|)
nonchilled 22.01916 2.148475 10.248740 9.463480e-13
chilled 16.98142 2.743761 6.189103 2.562416e-07
conc
Estimate Std. Error t value Pr(>|t|)
nonchilled 0.01982458 0.004091379 4.845452 1.934996e-05
chilled 0.01563659 0.005224992 2.992653 4.721873e-03
I suppose that, while subtle, this could make this approach error prone
for those who (like me in this case) miss it...
Then of course, we get down to the format of the output, etc.
:-)
Thanks Gabor,
Marc
More information about the R-help
mailing list