[R] Inverse Prediction with splines

[David Winsemius]

On Jan 20, 2011, at 2:37 PM, <Jeffrey.Morris at sanofipasteur.com> <Jeffrey.Morris at sanofipasteur.com 
 > wrote:

> Hello, I have fit a simple spline model to the following data.
>
> Data
> x	y
> 0	1.298
> 2	0.605
> 3	0.507
> 4	0.399
> 5	0.281
> 6	0.203
> 7	0.150
> 8	0.101
>
> Model
> Sp.1=lm(y~bs(x,df=4))
>
> Now I wish to inverse predict the x for y=.75, say.  Optimize works  
> fine
> for a polynomial but I can figure out how to get the spline model into
> the function argument.

Why not pass the reversed x and y vectors from the spline fit to  
approxfun()?

 > pred.Spl <- predict(Sp.1, data.frame(x=seq(0,8, by=0.01)  ) )

 > approxfun(x=pred.Spl, y=seq(0,8, by=0.01) )(0.75)
[1] 1.447311

Looks plausible, anyway.

-- 
David.
>
> Can anyone help me out.
>
> Thanks!!
>
> Jeff
>
> Jeff Morris
> Sanofi Pasteur
>
>
>
> This communication, including any attachments, is intended solely  
> for the use of the addressee and may contain information which is  
> privileged, confidential, exempt from disclosure under applicable  
> law or subject to copyright. If you are not an intended recipient,  
> any use, disclosure, distribution, reproduction, review or copying  
> is unauthorized and may be unlawful. If you have received this  
> transmission in error, please notify the sender immediately. Thank  
> you.
>
> Cette communication,y compris les pieces jointes, est reservee a  
> l'usage exclusif du destinataire et peut contenir des informations  
> privilegiees, confidentielles, exemptees de divulgation selon la loi  
> ou protegees par les droits de publication. Si vous n'etes pas un  
> destinataire, toute utilisation, divulgation, distribution,  
> reproduction, examen ou copie est non-autorisee et peut etre  
> illegale. Si vous avez recu cette communication par erreur, veuillez  
> aviser l'expediteur immediatement. Merci.
> 					
>
> 	[[alternative HTML version deleted]]
>
> ______________________________________________
> 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.

David Winsemius, MD
West Hartford, CT