Z = SMOOTH1Q(Y,S) smoothes the data Y using a DCT- or FFT-based spline smoothing method. Non finite data (NaN or Inf) are treated as missing values.
S is the smoothing parameter. It must be a real positive scalar. The larger S is, the smoother the output will be. If S is empty (i.e. S = ), it is automatically determined by minimizing the generalized cross-validation (GCV) score.
Z = SMOOTH1Q(...,'robust') carries out a robust smoothing that minimizes the influence of outlying data.
Z = SMOOTH1Q(...,'periodic') assumes that the data to be smoothed must be periodic.
[Z,S] = SMOOTH1Q(...) also returns the calculated value for the smoothness parameter S so that you can fine-tune the smoothing subsequently if required.
SMOOTH1Q is a simplified and quick version of SMOOTHN for 1-D data. If you want to smooth N-D arrays use SMOOTHN.
1) Garcia D, Robust smoothing of gridded data in one and higher dimensions with missing values. Computational Statistics & Data Analysis, 2010.
2) Buckley MJ, Fast computation of a discretized thin-plate smoothing spline for image data. Biometrika, 1994.
Changes in the "bisquare" subfunction