User defined function in curve fitter

[steven.f.lee]

Hey Guys

Does anyone know of anyway to get ImageJ to fit an arbitrary function using the curve fitter tool, rather than just exponential, linear, Gaussian, etc.

I'd like ideally to define a function and extract not only the fit parameters but also the uncertainties

Is there any easy way? Or should I just stick to MatLab

Many thanks in advance

Steve Lee

[Wayne Rasband]

On May 29, 2009, at 4:47 PM, steven.f.lee wrote:

> Hey Guys
>
> Does anyone know of anyway to get ImageJ to fit an arbitrary function
> using
> the curve fitter tool, rather than just exponential, linear, Gaussian,
> etc.
>
> I'd like ideally to define a function and extract not only the fit
> parameters but also the uncertainties
>
> Is there any easy way? Or should I just stick to MatLab
>
> Many thanks in advance

Upgrade to ImageJ 1.42f or later, which adds the ability to fit
user-defined functions to the curve fitting tool (Analyze>Tools>Curve
Fitting).

-wayne

[steven.f.lee]

Wayne

Yeah, I've read that, however when I open version 1.42o and go to the curve fitting I don't get the option on the drop down list

I've installed older versions and get the same problem

I am doing something stupid?

Thanks again, Steve
>

Wayne Rasband wrote

On May 29, 2009, at 4:47 PM, steven.f.lee wrote:

> Hey Guys
>
> Does anyone know of anyway to get ImageJ to fit an arbitrary function using
> the curve fitter tool, rather than just exponential, linear, Gaussian,
> etc.
>
> I'd like ideally to define a function and extract not only the fit
> parameters but also the uncertainties
>
> Is there any easy way? Or should I just stick to MatLab
>
> Many thanks in advance

Upgrade to ImageJ 1.42f or later, which adds the ability to fit
user-defined functions to the curve fitting tool (Analyze>Tools>Curve
Fitting).

-wayne

[Gabriel Landini]

On Friday 29 May 2009, steven.f.lee wrote:
> Wayne
>
> Yeah, I've read that, however when I open version 1.42o and go to the curve
> fitting I don't get the option on the drop down list

No? That is strange. What is the last item in the list after you scrolled
down?

G

[steven.f.lee]

OK, I've got it working now, thanks for all the help

One more question, is there any easy way to extract the errors of individual fit parameters from the curve fit?

Thanks guys!

Steve

Gabriel Landini wrote

On Friday 29 May 2009, steven.f.lee wrote:
> Wayne
>
> Yeah, I've read that, however when I open version 1.42o and go to the curve
> fitting I don't get the option on the drop down list

No? That is strange. What is the last item in the list after you scrolled
down?

G