What is the difference between polyfit and curve fitting

Hi

What is the difference between polyfit and curve fitting ?

would you please see this page explain me these command:

modelFun =  @(p,x) p(3) .* (x ./ p(1)).^(p(2)-1) .* exp(-(x ./ p(1)).^p(2));

startingVals = [10 2 5];

coefEsts = nlinfit(time, conc, modelFun, startingVals);

xgrid = linspace(0,20,100);

line(xgrid, modelFun(coefEsts, xgrid), 'Color','r');

And The Page Is:

http://www.mathworks.com/products/statistics/examples.html?file=/products/demos/shipping/stats/cfitdfitdemo.html

[Masoud Ghanbari]

The typed command is on the selected page also

THNX

Answer 1

[Shashank Prasanna]

I would encourage you to look at the documentation page of the functions you are you using to get a better idea of what each function is suited for.

POLYFIT:

http://www.mathworks.com/help/matlab/ref/polyfit.html

As Matt J mentioned is used to fit polynomials

NLINFIT:

http://www.mathworks.com/help/stats/nlinfit.html

Is non linear fitting/regression for models that need not be polynomials, but can be. Go through the examples in the above links to get a better idea.

[Masoud Ghanbari]

Hi Dear Shashank and thanks Dear Matt J

there is still a misunderstanding for me. i have a set of (x,y) dots and i want the function passes them as the best way .

which kind of fitting and regression should i use???

Or Which command (to be more clear)?

[Matt J]

You need to decide first what kind of function gives a good model for your (x,y) data. If the (x,y) data come from a polynomial, use POLYFIT. If they come from a more complicated function, use NLINFIT.

[Masoud Ghanbari]

Thanks Dear Matt J

Answer 2

[Matt J]

POLYFIT applies to polynomial fitting only.

[Armani]

That's correct! POLYFIT is a function specifically designed for fitting polynomial curves to data.

POLYFIT returns the coefficients of the fitted polynomial. These coefficients can be used to create the equation of the polynomial curve, getaway shootout can then be used for various purposes such as prediction, interpolation, or smoothing.