Polyfit is giving incorrect coefficients for correct plot fit.

8 Ansichten (letzte 30 Tage)
N O'SS
N O'SS am 26 Nov. 2019
Kommentiert: N O'SS am 27 Nov. 2019
So when using polyfit I get a really nice line ploted and matches my data well. Unfortunately when I go to use the coefficients determined by polyfit, it doesn't make sense at all! My expected slope c(1) is around 0.3 but I'm getting around 6. Even when I do the approximate calculation of the slope by hand it is as expected so my data mustn't be wrong.
Here's my code...
N=10:10:60;
t1 = [3.5 6.5 10 12.5 15.5 19];
t2 = [3 6.5 10 13 16 20];
t3 = [3 7 10.5 13.5 17 20];
t4 = [4 7 10 13 16.5 20];
t5 = [3.5 7 11 14.5 18 20.5];
T = [t1;t2;t3;t4;t5];
m = mean(T);
%Linear fit using polyfit
[c,S,mu] = polyfit(N,m,1);
%Error values of coefficients
ci = polyparci(c,S);
% Display evaluated equation y = m*x + b and the wavelength (desired to be approx. 0.6 micrometers)
disp(['Equation is y = ' num2str(c(1)) '*x + ' num2str(c(2))])
disp(['Wavelength is ' num2str(2.*c(1)) ' micrometers'])
% Evaluate fit equation using polyval
[y_est, delta] = polyval(c,N,S,mu);
%Polyfit function from coefficients
f = c(1)*N + c(2);
hold on
%Plotting of data
scatter(N,m,'b')
%Plotting of linear fit from polyval
plot(N,y_est,'r')
%Plotting of linear fit from function with coefficients
plot(N,f,'g')
%Labelling axes and plot etc...
hold off
I've added a plot of the function of the function with the coefficients
f = c(1)*N + c(2);
plot(N,f,'g')
to show how they are incorrect. This is the plot it outputs.
I thought I used polyfit correctly but I must not have. Where have I gone wrong?

Akzeptierte Antwort

Stijn Haenen
Stijn Haenen am 26 Nov. 2019
If I run this script i get a good fit, see image
N=10:10:60;
t1 = [3.5 6.5 10 12.5 15.5 19];
t2 = [3 6.5 10 13 16 20];
t3 = [3 7 10.5 13.5 17 20];
t4 = [4 7 10 13 16.5 20];
t5 = [3.5 7 11 14.5 18 20.5];
T = [t1;t2;t3;t4;t5];
m = mean(T);
[c] = polyfit(N,m,1);
f = c(1)*N + c(2);
plot(N,f,'g')
hold on
scatter(N,m,'b')
  1 Kommentar
N O'SS
N O'SS am 27 Nov. 2019
Ah it worked when I removed the mu from the equation and it worked. Why does that happen? I thought mu just helps with calculating the error, but as I removed it the errors still worked.
Thank you for your help!

Melden Sie sich an, um zu kommentieren.

Weitere Antworten (0)

Kategorien

Mehr zu Get Started with Curve Fitting Toolbox finden Sie in Help Center und File Exchange

Produkte


Version

R2018a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by