[BioC] Multitest!
Puhong Gao
pgao@hunter.cuny.edu
Mon, 18 Nov 2002 13:25:28 -0500
This is a multi-part message in MIME format.
------=_NextPart_000_001F_01C28F05.F5E7C1D0
Content-Type: text/plain;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
Hi, Dr. Dudoit,
Thank your group very much for the multtest package.
In reading your reply to Donglei's question, I am not sure how you got =
the the df (11.049) for Golub data. Can you explain that? Thanks.
Regards,
Puhong Gao, PhD
Dept. of Developmental Psychobiology
NYSPI/Columbia University
1051 Riverside Drive
New York, NY 10032
(212) 543-3710
From: Sandrine Dudoit <sandrine@stat.berkeley.edu>
Date: Sat, 19 Oct 2002 20:46:03 -0700 (PDT)
To: <donghu@itsa.ucsf.edu>
Cc: Bioconductor mailing list <bioconductor@stat.math.ethz.ch>
Subject: Re: [BioC] Help with raw p-value
Hi,
The p-values in rawp0 are calculated based on a standard normal
distribution, while those in t.test are calculated based on a
t-distribution with df =3D 11.049.
Try
2*(1-pt(abs(teststat[1]),df=3D11.049))
and you will get the same p-value as with t.test.
Sandrine
-------------------------------------------------------------------------=
---
---
Sandrine Dudoit, Ph.D. E-mail: sandrine@stat.berkeley.edu
Assistant Professor Tel: (510) 643-1108
Division of Biostatistics Fax: (510) 643-5163
School of Public Health =
http://www.stat.berkeley.edu/~sandrine
University of California, Berkeley
140 Earl Warren Hall, #7360
Berkeley, CA 94720-7360
-------------------------------------------------------------------------=
---
---
On Wed, 16 Oct 2002 donghu@itsa.ucsf.edu wrote:
> I have played with multtest package using Golub data. After loading =
the
> dataset, I followed the steps descripted in the document to calculate =
t
> stat and raw p-values. Here are what I did:
>
> >teststat <- mt.teststat(golub, golub.cl)
> >rawp0 <- 2*(1-pnorm(abs(teststat)))
>
> Then I took a look of the t stat and raw p-value of the first gene. I =
got:
>
> >teststat[1]
> [1] 1.759195
> >rawp0[1]
> [1] 0.07854436
>
> I also tried to calculate t stat and p-value of the first gene using
> t.test. I did the followings.
>
> > x <- golub[1,1:27]
> > y <- golub[1,28:38]
> > t.test(x,y)
>
> The result showed "t =3D -1.7592" and "p-value =3D 0.1062". I don't
> understand why the "p-value" I got here is different from "rawp0[1]"
> although the t stat is same. Can someone let me know why? Thank you =
in
> advance.
>
> Donglei Hu
> Gene Array Core Lab
> Diabetes Center
> UCSF
>
>
> _______________________________________________
> Bioconductor mailing list
> Bioconductor@stat.math.ethz.ch
> http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor
>
_______________________________________________
Bioconductor mailing list
Bioconductor@stat.math.ethz.ch
http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor
------=_NextPart_000_001F_01C28F05.F5E7C1D0
Content-Type: text/html;
charset="iso-8859-1"
Content-Transfer-Encoding: quoted-printable
<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">
<HTML><HEAD>
<META http-equiv=3DContent-Type content=3D"text/html; =
charset=3Diso-8859-1">
<META content=3D"MSHTML 6.00.2800.1106" name=3DGENERATOR>
<STYLE></STYLE>
</HEAD>
<BODY bgColor=3D#ffffff>
<DIV><FONT face=3DArial size=3D2>Hi, Dr. Dudoit,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>Thank your group very much for the =
multtest=20
package.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>In reading your reply to Donglei's =
question,=20
I am not sure how you got the the df (11.049) for Golub =
data. Can=20
you explain that? Thanks.</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>Regards,</FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2>Puhong Gao, PhD<BR>Dept. of =
Developmental=20
Psychobiology<BR>NYSPI/Columbia University<BR>1051 Riverside =
Drive<BR>New York,=20
NY 10032<BR>(212) 543-3710<BR></FONT></DIV>
<DIV><FONT face=3DArial size=3D2></FONT> </DIV>
<DIV><FONT face=3DArial size=3D2><FONT face=3D"Times New Roman" =
size=3D3>From: Sandrine=20
Dudoit <</FONT><A href=3D"mailto:sandrine@stat.berkeley.edu"><FONT=20
face=3D"Times New Roman" =
size=3D3>sandrine@stat.berkeley.edu</FONT></A><FONT=20
face=3D"Times New Roman" size=3D3>><BR>Date: Sat, 19 Oct 2002 =
20:46:03 -0700=20
(PDT)<BR>To: <</FONT><A href=3D"mailto:donghu@itsa.ucsf.edu"><FONT=20
face=3D"Times New Roman" size=3D3>donghu@itsa.ucsf.edu</FONT></A><FONT=20
face=3D"Times New Roman" size=3D3>><BR>Cc: Bioconductor mailing list=20
<</FONT><A href=3D"mailto:bioconductor@stat.math.ethz.ch"><FONT=20
face=3D"Times New Roman" =
size=3D3>bioconductor@stat.math.ethz.ch</FONT></A><FONT=20
face=3D"Times New Roman" size=3D3>><BR>Subject: Re: [BioC] Help with =
raw=20
p-value<BR><BR>Hi,<BR><BR>The p-values in rawp0 are calculated based on =
a=20
standard normal<BR>distribution, while those in t.test are calculated =
based on=20
a<BR>t-distribution with df =3D=20
11.049.<BR><BR>Try<BR>2*(1-pt(abs(teststat[1]),df=3D11.049))<BR>and you =
will get=20
the same p-value as with=20
t.test.<BR><BR>Sandrine<BR><BR>------------------------------------------=
----------------------------------<BR>---<BR>Sandrine=20
Dudoit,=20
Ph.D. &n=
bsp; =20
E-mail: </FONT><A href=3D"mailto:sandrine@stat.berkeley.edu"><FONT=20
face=3D"Times New Roman" =
size=3D3>sandrine@stat.berkeley.edu</FONT></A><BR><FONT=20
face=3D"Times New Roman" size=3D3>Assistant=20
Professor &nbs=
p; =20
Tel: (510) 643-1108<BR>Division of=20
Biostatistics =
=20
Fax: (510) 643-5163<BR>School of Public=20
Health &=
nbsp;=20
</FONT><A href=3D"http://www.stat.berkeley.edu/~sandrine"><FONT=20
face=3D"Times New Roman"=20
size=3D3>http://www.stat.berkeley.edu/~sandrine</FONT></A><BR><FONT=20
face=3D"Times New Roman" size=3D3>University of California, =
Berkeley<BR>140 Earl=20
Warren Hall, #7360<BR>Berkeley, CA=20
94720-7360<BR>-----------------------------------------------------------=
-----------------<BR>---<BR><BR>On=20
Wed, 16 Oct 2002 </FONT><A href=3D"mailto:donghu@itsa.ucsf.edu"><FONT=20
face=3D"Times New Roman" size=3D3>donghu@itsa.ucsf.edu</FONT></A><FONT=20
face=3D"Times New Roman" size=3D3> wrote:<BR><BR>> I have played with =
multtest=20
package using Golub data. After loading the<BR>> dataset, I =
followed=20
the steps descripted in the document to calculate t<BR>> stat and raw =
p-values. Here are what I did:<BR>><BR>> >teststat <-=20
mt.teststat(golub, golub.cl)<BR>> >rawp0 <-=20
2*(1-pnorm(abs(teststat)))<BR>><BR>> Then I took a look of the t =
stat and=20
raw p-value of the first gene. I got:<BR>><BR>>=20
>teststat[1]<BR>> [1] 1.759195<BR>> >rawp0[1]<BR>> [1]=20
0.07854436<BR>><BR>> I also tried to calculate t stat and p-value =
of the=20
first gene using<BR>> t.test. I did the =
followings.<BR>><BR>>=20
> x <- golub[1,1:27]<BR>> > y <- golub[1,28:38]<BR>> =
>=20
t.test(x,y)<BR>><BR>> The result showed "t =3D -1.7592" and =
"p-value =3D=20
0.1062". I don't<BR>> understand why the "p-value" I got here =
is=20
different from "rawp0[1]"<BR>> although the t stat is same. Can =
someone=20
let me know why? Thank you in<BR>> advance.<BR>><BR>> =
Donglei=20
Hu<BR>> Gene Array Core Lab<BR>> Diabetes Center<BR>>=20
UCSF<BR>><BR>><BR>>=20
_______________________________________________<BR>> Bioconductor =
mailing=20
list<BR>> </FONT><A =
href=3D"mailto:Bioconductor@stat.math.ethz.ch"><FONT=20
face=3D"Times New Roman" =
size=3D3>Bioconductor@stat.math.ethz.ch</FONT></A><BR><FONT=20
face=3D"Times New Roman" size=3D3>> </FONT><A=20
href=3D"http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor"><FONT=
=20
face=3D"Times New Roman"=20
size=3D3>http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor</FONT=
></A><BR><FONT=20
face=3D"Times New Roman"=20
size=3D3>><BR><BR>_______________________________________________<BR>B=
ioconductor=20
mailing list<BR></FONT><A =
href=3D"mailto:Bioconductor@stat.math.ethz.ch"><FONT=20
face=3D"Times New Roman" =
size=3D3>Bioconductor@stat.math.ethz.ch</FONT></A><BR><A=20
href=3D"http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor"><FONT=
=20
face=3D"Times New Roman"=20
size=3D3>http://www.stat.math.ethz.ch/mailman/listinfo/bioconductor</FONT=
></A><BR><BR></DIV></FONT></BODY></HTML>
------=_NextPart_000_001F_01C28F05.F5E7C1D0--