@stat.math.ethz.ch
Subject: [R] LSD, HSD,...
Hi,
I'm designing a experiment in order to compare the growing of
several clones of a tree specie. It will be a complete randomized block
design. How can I decide what model of mean comparision to choose? LSD,
HSD,TukeyHSD, Duncan,...? Thanks in ad
On Tue, 17 Jul 2007, John Maindonald wrote:
> Stepwise regression variable selection
> methods make multiple post hoc comparisons. The
Some do, but step() (the only way offered in base R) does not test at all.
> number of comparisons may be very large, vastly more
> than the half-dozen post-ho
Stepwise regression variable selection
methods make multiple post hoc comparisons. The
number of comparisons may be very large, vastly more
than the half-dozen post-hoc comparisons that are
common in an experimental design context.
There is a disconnect here. The multiple testing issue is
noted
If you have a priori planned comparisons, you can just test those using
linear contrasts, with no need to correct for multiple testing. If you
do not, and you are relying on looking at the data and analysis to tell
you which treatment means to compare, and you are considering several
tests, then yo
Hi,
I'm designing a experiment in order to compare the growing of
several clones of a tree specie. It will be a complete randomized block
design. How can I decide what model of mean comparision to choose? LSD,
HSD,TukeyHSD, Duncan,...? Thanks in advance
___