Re: Curve Fitting and Plotting

[Jaroslav Hajek]

On Fri, Sep 26, 2008 at 3:36 PM, Michael Creel <address@hidden> wrote:
> There are _many_ options, depending on what kind of fit you would
> like. You can get a nonparametric (kernel regression) fit to data
> distributed randomly around a straight line using something like
>
> x = (1:100)/100';
> y = x + randn(100,1);
> f = kernel_regression(x,y,x);
> plot(x, [y f])
>
> This requires the econometrics package in Octave Forge. For this data,
> the ols fit (do help ols for more info) would be a better choice,
> though. Just an example that a lot of options are available.
>

Another option is the octgpr package, which will try to auto-estimate
the kernel width and white noise rate.

> Michael
>
> On Fri, Sep 26, 2008 at 12:32 PM, Kearan Mc Pherson
> <address@hidden> wrote:
>> Hi
>>
>> I am new to Octave and Gnuplot. I need help on fitting a curve through a
>> data.dat file, that contains values x an y in column format.
>> Any ideas where to start?
>>
>> Kind regadrs
>>
>> _______________________________________________
>> Help-octave mailing list
>> address@hidden
>> https://www-old.cae.wisc.edu/mailman/listinfo/help-octave
>>
>>
> _______________________________________________
> Help-octave mailing list
> address@hidden
> https://www-old.cae.wisc.edu/mailman/listinfo/help-octave
>



-- 
RNDr. Jaroslav Hajek
computing expert
Aeronautical Research and Test Institute (VZLU)
Prague, Czech Republic
url: www.highegg.matfyz.cz