MATLAB Answers

Locks

error message using polyfit (nonlinear regression)

Asked by Locks
on 20 Apr 2013
Accepted Answer by bym

hi,

I get the following error meesage:

    Warning: Polynomial is not unique; degree >= number of data points. 
    > In polyfit at 71
      In deltaAdjustment at 27
      In run at 74 

The code I am using is the following:

for putCall =1:2
    dataPutCall = data16(data16(:,3)==putCall,:);
    dates=unique(dataPutCall(:,6));
    for i=1:length(dates)
        date=dates(i);
        dataDate = dataPutCall(dataPutCall(:,6) == date,:);
        Ts = unique(dataDate(:,5));
        for indexT = 1:length(Ts)
            T = Ts(indexT);
            dataT = dataDate(dataDate(:,5) == T,:);
                number=dataT(:,13);  
                x= dataT(:,2);
                y=dataT(:,10);
                p = polyfit(x,y,2);
                f = polyval(p,x);
                a=p(3);
                b=p(2);
                c=p(1);
                SlopeSkew(number)=b+2*c.*x;
                Slope=SlopeSkew';
            end
        end
    end

I have used this code for a smaller matrix and there is was worked perfectly but not it seems as something is not working correctly and I am unsure what excatly it is

  0 Comments

Products

No products are associated with this question.

1 Answer

bym
Answer by bym
on 20 Apr 2013
 Accepted answer

I think it is obvious from the message; you don't have a enough data points to fit the polynomial uniquely. Like fitting a line through just one point, there are many solutions

x=[1,2];
y = [2,8];
polyfit(x,y,2)
Warning: Polynomial is not unique; degree >= number of data points. 
> In polyfit at 72

  3 Comments

Locks
on 21 Apr 2013

You're right, I didn't get it at first because it's working for a smaller dataset. I assume when using polyfit(x,y,2), there are at least three inputs needed to compute the curve up to power of 2, is that correct?

Walter Roberson
on 21 Apr 2013

Yes, at least n+1 points for degree n.

Locks
on 21 Apr 2013

perfect, thanks


Discover what MATLAB® can do for your career.

Opportunities for recent engineering grads.

Apply today