[RsR] Robust nonlinear regression in R

[Ruckstuhl Andreas (rkst)]

Dear Dorst

There are some good advices on how to generate good starting values in the book of Bates and Watts ("Nonlinear Regression Analysis & Its Applications", Wiley 1988).

Hint:
In partial linear problems, a linear regression model can be fitted to generate stating values. Make sure you use robust fitting procedures because they produce more reliable stating values usually (just my experience).

All the best
Andreas


>> -----Ursprüngliche Nachricht-----
>> Von: r-sig-robust-bounces using r-project.org 
>> [mailto:r-sig-robust-bounces using r-project.org] Im Auftrag von 
>> khanx131 using umn.edu
>> Gesendet: Sonntag, 19. Oktober 2008 20:21
>> An: r-sig-robust using r-project.org
>> Betreff: Re: [RsR] Robust nonlinear regression in R
>> 
>> 
>> Thanks to all, I looked into the nonlinear regression 
>> fitting function 
>> "nlrob()" available in R. the problem with it is that unless 
>> i don't get 
>> start with good starting values close to the actual one's it 
>> does not work. 
>> Is there any pointers how to choose good starting values-?
>> 
>> Thanks,
>> Dost.
>> 
>> 
>> On Sep 26 2008, Tobias Verbeke wrote:
>> 
>> >From the Robust Statistical Methods Task View on CRAN
>> >at
>> >
>> >http://cran.r-project.org/web/views/Robust.html
>> >
>> >
>> > " Robust Nonlinear model fitting is available through 
>> robustbase 's 
>> > nlrob()."
>> >
>> >install.packages("robustbase")
>> >library(robustbase)
>> >?nlrob
>> >
>> >HTH,
>> >Tobias
>> >
>> >> I would like to know about robust nonlinear regression R 
>> code as well.
>> >>
>> >> Arny
>> >>
>> >>
>> >> Arnold J. Stromberg
>> >> Professor and Chair
>> >> Department of Statistics
>> >> University of Kentucky
>> >> 817 Patterson Office Tower
>> >> Lexington, KY 40506-0027
>> >> Phone: 859-257-6115
>> >> Fax: 859-323-1973
>> >>
>> >>
>> >> -----Original Message----- From: 
>> r-sig-robust-bounces using r-project.org 
>> >> [mailto:r-sig-robust-bounces using r-project.org] On Behalf Of 
>> >> khanx131 using umn.edu Sent: Thursday, September 25, 2008 6:50 PM To: 
>> >> r-sig-robust using r-project.org Subject: [RsR] Robust 
>> nonlinear regression in 
>> >> R
>> >>
>> >> Hi dear linsters,
>> >>
>> >> I am starting work on a robust nonlinear regression 
>> project. Is there any
>> >> code, stuff in R for robust estimation of nonlinear 
>> regression functions.
>> >> any comments,material help, suggestions would be greatly 
>> appreciated.
>> >> thanks in advance,
>> >>
>> >> Dost.
>> >>
>> >> _______________________________________________
>> >> R-SIG-Robust using r-project.org mailing list
>> >> https://stat.ethz.ch/mailman/listinfo/r-sig-robust
>> >>
>> >> _______________________________________________
>> >> R-SIG-Robust using r-project.org mailing list
>> >> https://stat.ethz.ch/mailman/listinfo/r-sig-robust
>> >>
>> >>
>> >
>> >
>> >
>> 
>> _______________________________________________
>> R-SIG-Robust using r-project.org mailing list
>> https://stat.ethz.ch/mailman/listinfo/r-sig-robust
>>