User: Michael Benjamin
Michael Benjamin • 120
- Reputation:
- 120
- Status:
- Trusted
- Location:
- Last seen:
- 16 years ago
- Joined:
- 17 years ago
- Email:
- m******@bellsouth.net
Posts by Michael Benjamin
<prev
• 12 results •
page 1 of 2 •
next >
0
votes
2
answers
485
views
2
answers
... This is the most exciting, and cryptic, part of the message...
> which you can then normalize and scale. The normalizing and scaling
> can, of course also be split up across processors.
How?
I was able to use snow to split up the CEL file readings--it's
actually
not that hard.
cl<-makeC ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
2
answers
756
views
2
answers
Comment:
C: limma package
... Progress update (summarized from my forum for such matters at
http://www.theschedule.net/forum/gforum.cgi?forum=20&do=forum_view):
Briefly, I created a four-node cluster out of Pentium-III boxes and
Debian Linux/openMosix. I saw no significant performance boost of
ReadAffy or expresso using th ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
3
answers
598
views
3
answers
Answer:
A: (no subject)
... Thoughts:
XML installation is tough. Try manually downloading the package
source
.gz for as many versions as you can find, then install that. Try
installing the R XML package (not just the Bioconductor XML package).
Only the "devel" version of AnnBuilder, I think 1.3.5, installed for
me.
Good l ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
3
answers
544
views
3
answers
Comment:
C: Annotation Questions
... Inspired by Ramon Diaz-Uriarte, I wanted to see how R/Bioconductor
works
on a cluster. After a few false starts, I successfully linked three
lab
computers (my laptop, a P-III 750 and a P-4 1.7) using openMosix. I
found an easy solution in Cluster Knoppix, which magically turns Win-
2k
boxes into c ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
1
answer
477
views
1
answers
Comment:
C: Advice on cluster hardware
... Ramon:
That sounds like a tremendously exciting project! You seem to have
done
much research, and your solution should be both scalable and
reasonably
priced.
I have seen reports that R is "compatible" with openMosix, but I have
not found reports of real-world experience. Does R use shared memor ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
2
answers
422
views
2
answers
Comment:
C: From Limma to SAM
... Hi, all--
I wanted to start a thread on R speed/benchmarking. There is a nice R
benchmarking overview at http://www.sciviews.org/other/benchmark.htm,
along with a free script so you can see how your machine stacks up.
Looks like R is substantially faster than S-plus.
My problem is this: with 512 ...
written 16.0 years ago by
Michael Benjamin • 120
0
votes
6
answers
630
views
6
answers
Comment:
C: Re: Manova nuances
... This sounds very reasonable. I'm having a bit of trouble with the
implementation.
How do you solve for a variable? I know u * diag(d) * t(v) gets your
original data, but how do you pick variables? Just taking the first
four columns of u or v alone doesn't work--I tried. There must be a
way
to c ...
written 16.1 years ago by
Michael Benjamin • 120
0
votes
6
answers
630
views
6
answers
Comment:
C: Re: Manova nuances
... Can I do instead:
comps1<-svd(teset[group1])$d
comps2<-svd(teset[group2])$d
t.test(comps1,comps2)
Maybe I could just compare the top two or three components to one
another?
Mike
-----Original Message-----
From: Baker, Stephen [mailto:Stephen.Baker@umassmed.edu]
Sent: Friday, November 21, 20 ...
written 16.1 years ago by
Michael Benjamin • 120
0
votes
6
answers
630
views
6
answers
Comment:
C: Re: Manova nuances
... Yes, Dr. Liaw is closer to my desired goal of one summary statistic
for
a large number of variables. Is that possible with PCA?
I appreciate Dr. Baker's thoughts, though--I think PCA and manova have
similarities.
-----Original Message-----
From: Liaw, Andy [mailto:andy_liaw@merck.com]
Sent: Frida ...
written 16.1 years ago by
Michael Benjamin • 120
0
votes
1
answer
458
views
1
answers
...
Anybody here using manova? It's powerful and pretty fast, but I'm
finding that you can't have more variables than samples (limits its
applicability to microarray research). Is there any way around this?
Assume
dim(eset)
1200 35
transeset<-t(eset)
fit<-manova(transeset ~ categories)
summa ...
written 16.1 years ago by
Michael Benjamin • 120
Latest awards to Michael Benjamin
No awards yet. Soon to come :-)
Use of this site constitutes acceptance of our User
Agreement
and Privacy
Policy.
Powered by Biostar
version 16.09
Traffic: 318 users visited in the last hour