On 13/02/14 12:03, Andrea Graziani wrote:
Using the same starting values, the two approaches bring to slightly different
solutions:
### 1. Real part and Imaginary part
fit$estimate
[1] -3.8519181 -2.7342861 -1.4823740 1.7173982 4.4529298 1.4383334
0.1564904 0.4856774 2.2789567 3.
Hi Frede,
Thank you for your accurate answer!
If I understand well, your way to use nls() solves the problem using too many
physical parameters.
I solved the problem following the other way that you and Rolf Turner suggested
(i.e. splitting the complex-valued problem into two real-valued proble
Dear Rolf,
Thank you for your suggestion.
Based on your remarks I solved my problem using nlm().
Actually there are two quite straightforward ways to split the complex-valued
problem into two “linked” real-valued problems.
### 1. Real part and Imaginary part
# Experimental data
E1_data <- Re(E
On 11/02/2014 2:10 PM, David Winsemius wrote:
On Feb 9, 2014, at 2:45 PM, Andrea Graziani wrote:
> Hi everyone,
>
> I previously posted this question but my message was not well written and did
not contain any code so I will try to do a better job this time.
>
> The goal is to perform a non-lin
On Feb 9, 2014, at 2:45 PM, Andrea Graziani wrote:
> Hi everyone,
>
> I previously posted this question but my message was not well written and did
> not contain any code so I will try to do a better job this time.
>
> The goal is to perform a non-linear regression on complex-valued data.
> I
I have not the mental energy to go through your somewhat complicated
example, but I suspect that your problem is simply the following: The
function nls() is trying to minimize a sum of squares, and that does not
make sense in the context of complex observations. That is, nls() is
trying to
6 matches
Mail list logo
