[R] Better way to find function
nuvo nuvo
nuvolab at hotmail.com
Wed Jan 21 18:42:17 CET 2004
>From: "Liaw, Andy"
>To: "'nuvo nuvo'" ,r-help at stat.math.ethz.ch
>Subject: RE: [R] Better way to find function
>Date: Wed, 21 Jan 2004 09:10:06 -0500
>
>For #1, could you clarify what you mean by `function', an R function,
or a
>regression function?
I mean to choose a functional form automatically, e.g. 1/(
a+exp[b+cx]), a+bx, ... [ I saw some of the commercial software can do
it ].
>For #2, there are several packages on CRAN (and in the R distribution
>itself) that fit regression splines, if that's what you meant by
`piecewise
>regression'. For logistic regression, you can either use the bs()
term in
>glm(), or gam() in the `mgcv' package.
I don't want to use Spline, because I need the functional form and
also parameters. Moreover I have 3 independent variables, not only
one.
I want to do only 2 piecewise regression by using the logistic
function i.e. c/( 1+exp[a+bx]). Then it will be difficult where to put
the knot and also it may not be continuous at the knot.
>
>HTH,
>Andy
>
> > From: nuvo nuvo
> >
> > To whom it may concern,
> >
> > 1. I would like to know if there is a command in R to choose
> > a function for
> > a given dataset. I am facing a difficult question about how
> > to fit the data
> > [ please attachment ]
> >
> > 2. Are there any function that will allow users to do the
piecewise
> > regression?
> >
> > If not, is it going to be provide in the new updated version?
> > What I am
> > using is the piecewise logistic regression, but it doesn't
> > have a continuous
> > function though. I hope that R would have a specific command
> > to do the
> > piecewise (non)linear regression.
> >
> > I would apprecaite your suggestion.
> >
> > Sincerely yours,
> >
> > Nhum
> >
> > _________________________________________________________________
> > Rethink your business approach for the new year with the
> > helpful tips here.
> >
> > ______________________________________________
> > R-help at stat.math.ethz.ch mailing list
> > https://www.stat.math.ethz.ch/mailman/listinfo/r-help
> > PLEASE do read the posting guide!
> > http://www.R-project.org/posting-guide.html
> >
> >
>
>
>---------------------------------------------------------------------
---------
>Notice: This e-mail message, together with any attachments, contains
>information of Merck & Co., Inc. (One Merck Drive, Whitehouse
Station, New
>Jersey, USA 08889), and/or its affiliates (which may be known outside
the
>United States as Merck Frosst, Merck Sharp & Dohme or MSD and in
Japan, as
>Banyu) that may be confidential, proprietary copyrighted and/or
legally
>privileged. It is intended solely for the use of the individual or
entity
>named on this message. If you are not the intended recipient, and
have
>received this message in error, please notify us immediately by reply
e-mail
>and then delete it from your system.
>---------------------------------------------------------------------
---------
_________________________________________________________________
[1]Learn how to choose, serve, and enjoy wine at Wine @ MSN.
References
1. http://g.msn.com/8HMBENUS/2749??PS=
More information about the R-help
mailing list