[R] Please help me about the regress models!

Greg Snow Greg.Snow at imail.org
Wed Nov 12 17:38:20 CET 2008

I think what you need is a good consultant, and with that deadline don't expect any bargains.

You have not specified your problem with enough detail yet, 2 options (there are probably many more) include:

Use the nls function with the model as stated

Use the lm function starting as lm( log( 100/y - 1 ) ~ x,

Those 2 options are based on different models of how the error comes into play, which is more appropriate depends on things that we cannot guess at based on your description.  What to do with either model once fit also depends on the question you want answered.

Gregory (Greg) L. Snow Ph.D.
Statistical Data Center
Intermountain Healthcare
greg.snow at imail.org

> -----Original Message-----
> From: r-help-bounces at r-project.org [mailto:r-help-bounces at r-
> project.org] On Behalf Of Leon_Long
> Sent: Tuesday, November 11, 2008 8:33 PM
> To: r-help at r-project.org
> Subject: [R] Please help me about the regress models!
> I am a bigginer of R language.I need to prepare a PPT which deadline is
> 15
> Nov. 2008.  I want to build a regress model with my own formula. The
> formula
> is y=100/(1+exp(a+b*X)). I have no idea of the R program,please
> demonstrate
> how to do it or give a good sample.
> Anyone would help me? Thank you very much!
> --
> View this message in context: http://www.nabble.com/Please-help-me-
> about-the-regress-models%21-tp20453522p20453522.html
> Sent from the R help mailing list archive at Nabble.com.
> ______________________________________________
> R-help at r-project.org mailing list
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide http://www.R-project.org/posting-
> guide.html
> and provide commented, minimal, self-contained, reproducible code.

More information about the R-help mailing list