Re: [R] qt with ncp?

From: Peter Malewski (peter.malewski@gmx.de)
Date: Tue 08 May 2001 - 02:53:12 EST

• Next message: Tak Kaneko: "[R] "tree": Extracting deviance & Gaussian model of the node?"
• Previous message: Chong Gu: "Re: [R] gss package - predict.ssanova"
• In reply to: Peter Dalgaard BSA: "Re: [R] qt with ncp?"

Message-ID: <20010507185311.B29936@rzpool08.rz.tu-bs.de>

On Mon, May 07, 2001 at 06:45:32PM +0200, Peter Dalgaard BSA wrote:
> Peter Malewski <peter.malewski@gmx.de> writes:
>
> > Does anybody has a function or idea how to calculate qt with a noncentrality
> > parameter? I'm porting a SAS-macro for equivalence (Wellek, 1994 TT2ST) to R
> > and it seems that I need this to calculate tinv (SAS-command, I hope that
> > this is R's qt,...I get the SAS-macro manual next week).
>
> The easiest way is probably to use something like
>
> uniroot(function(x)pt(x, df, ncp) - p, c(-1e7,1e7))
>
> It's not going to be fast, but if you just need one of them...
>
> (Look inside power.t.test for variations on the theme)

Thanks for that hint. I'll see.
Peter

-- 
P.Malewski, Limmerstr.47, 30451 Hannover, 0511-2135008
At work: http://www.MH-Hannover.de 0511 532 3194 / Fax: 0511 532 3190, 
P.Malewski@tu-bs.de, peter.malewski@gmx.de, malewski.peter@mh-hannover.de.
-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-.-
r-help mailing list -- Read http://www.ci.tuwien.ac.at/~hornik/R/R-FAQ.html
Send "info", "help", or "[un]subscribe"
(in the "body", not the subject !)  To: r-help-request@stat.math.ethz.ch
_._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._._

• Next message: Tak Kaneko: "[R] "tree": Extracting deviance & Gaussian model of the node?"
• Previous message: Chong Gu: "Re: [R] gss package - predict.ssanova"
• In reply to: Peter Dalgaard BSA: "Re: [R] qt with ncp?"

This archive was generated by hypermail 2b30 : Fri 22 Jun 2001 - 18:58:41 EST