How to Interpolated data outliers

I have a data column that has 3630 rows of data. I used the method: [A, B] = rmoutliers (C, 'movmedian', window); to remove the data outliers.

These data were removed and I need them to be interpolated by the average of the entire column of data. How can I do this?

Answer 1

[Turlough Hughes]

Generate some sample data:

C = (1:3630).';
idxout = randperm(3630,500); % random index for outliers
C(idxout) = C(idxout)+2000*(1-2*rand(numel(idxout),1));

Using rmoutliers some of the values are removed:

window = 50;
[A, B] = rmoutliers(C, 'movmedian', window);

Seeing as you've indicated that you only have a column vector of data I assume you want to interpolate using index position as your input for x, you could try the following:

idx = find(~B); % C(idx) is the same as A
D = interp1(idx,A,1:size(C,1)); % Interpolated using index position as x values.

Let me know.

[Turlough Hughes]

Did this work for you? If not I suggest uploadibg the variable C as a .mat

Answer 2

[Matheus Brito]

Hi Turlough

Yes, it worked very well and I was able to perform the procedures I needed.

Thank you!

[Turlough Hughes]

No problem. In that case can you accept it?

[Matheus Brito]

Done!

[Matheus Brito]

Hi Turlough Hughes, how are you?

Can you help me again? After interpolation, in some cases matlab gave me the following information:

Error using eig

Input matrix contains NaN or Inf.

Do you know why this may be happening? And how can I solve this? So to calculate some variables such as area, amplitude, frequency and others?

Thanks