Greetings to all,
First off, I want to thank you all for answering any nagging questions
I've had over the past few days. I've been in the process of putting
together A Quick and (Very) Dirty Intro to Doing Your Statistics in R
(which I have posted to http://didemnid.ucdavis.edu/rtutorial.html ) in
order to teach an R workshop for the graduate students in my
department. This is a guide for your everyday stats crunchers who want
to free themselves from the cycle of SAS updates, have more flexibility
than JMP or Statview will allow, but are not hardcore
programming/think-about-stats-allday types. These are people who get
data from the natural world, and then find out what it's telling them.
So, to that end, I've put the guide together, and would be very
interested in any comments you all would have. Are there any
statistical methods that you think I really should have included for
this type of audience that I didn't (and if it's over my head, would
you be interested in contributing)? Is there anything just blatantly
wrong or is unclear to a casual reader?
Most importantly, there are still a few holes that need to be filled -
if they can be
1) A SIMPLE explanation for how to do mixed models using lme. I am
quite unsatisfied with most of what I've seen on the net, and if it
even comes close to going over my head, it really won't fly with most
folk I know. I've done the best I can, but I know if falls short.
2) A method of looking at type II and III sums of squares for aov if
there is a different error term included.
3) How does one plot canonical values and centroid groupings for a
MANOVA?
4) How does one use manova to do repeated measures? I've got the
univariate method down, but would like to use manova a la the repeated
statement in SAS.
5) Better output for post-hocs, and a Ryan's Q implementation.
Thanks in advance for any input, and I hope this can be a resource to a
lot of people!
----------------------------------------
Jarrett Byrnes
Population Biology Graduate Group, UC Davis
Bodega Marine Lab
707-875-1969
http://www-eve.ucdavis.edu/stachowicz/byrnes.shtml