R help - Aug 2009 - solving system of equations involving non-linearities

Hi,

I would appreciate if someone could help me on track with this problem.

I want to compute some parameters from a system of equations given a number of
sample observations. The system looks like this:

sum_i( A+b_i>0 & A+b_i>C+d_i) = x
sum_i( C+d_i>0 & C+d_i>A+b_i) = y
sum_i( exp(E+f_i) * ( A+b_i>0 & A+b_i>C+d_i) = z

A, C, E are free variables while the other letters represent values given from
sample observations. The equations involve counts of the number of fulfilled
conditions and therefore non-linearities. Furthermore, since I have many
observations i, the equations will unlikely hold exactly and solving will
require some closeness measure like the sum of the squared deviations or so.

Is there any function in R suitable for solving this problem?

Thanks so much for your help,
  Werner

You have two options:

1.  The `BBsolve' function in the "BB" package to solve this
system of 3 equations.
2.  Try `nleqslv' function in the "nleqslv" package.

These would work even if the residual is not zero.

Hope this helps,
Ravi.
____________________________________________________________________

Ravi Varadhan, Ph.D.
Assistant Professor,
Division of Geriatric Medicine and Gerontology
School of Medicine
Johns Hopkins University

Ph. (410) 502-2619
email: rvaradhan at jhmi.edu


----- Original Message -----
From: Werner Wernersen <pensterfuzzer at yahoo.de>
Date: Thursday, August 6, 2009 7:56 am
Subject: [R] solving system of equations involving non-linearities
To: r-help at stat.math.ethz.ch

> Hi,
>  
>  I would appreciate if someone could help me on track with this problem.
>  
>  I want to compute some parameters from a system of equations given a 
> number of sample observations. The system looks like this:
>  
>  sum_i( A+b_i>0 & A+b_i>C+d_i) = x
>  sum_i( C+d_i>0 & C+d_i>A+b_i) = y
>  sum_i( exp(E+f_i) * ( A+b_i>0 & A+b_i>C+d_i) = z
>  
>  A, C, E are free variables while the other letters represent values 
> given from sample observations. The equations involve counts of the 
> number of fulfilled conditions and therefore non-linearities. 
> Furthermore, since I have many observations i, the equations will 
> unlikely hold exactly and solving will require some closeness measure 
> like the sum of the squared deviations or so.
>  
>  Is there any function in R suitable for solving this problem?
>  
>  Thanks so much for your help,
>    Werner
>  
>  
>  
>  
>  
>  ______________________________________________
>  R-help at r-project.org mailing list
>  
>  PLEASE do read the posting guide 
>  and provide commented, minimal, self-contained, reproducible code.