Regression, the periodogram, and the Lomb-Scargle periodogram

Barry G. Quinn

ICASSP 2016accepted0 citations

Regression, the periodogram, and the Lomb-Scargle periodogram

Abstract

In [1], Lomb developed a nonlinear regression approach to estimating the frequency of a noisy sinusoid when the measurement times were not equispaced, and a method for correcting the times so that the resulting regression sum of squares appeared very similar to the usual periodogram. Scargle [2] suggested that the usual periodogram be discarded, and replaced by the new version, which has become known as the Lomb-Scargle periodogram. In this paper, we extend Lomb's development to include a `DC' term. We show why it is important to include this term, especially when the times are irregular or the frequency low.

BibTeX

@inproceedings{icassp2016_regressiontheper,
  title = {Regression, the periodogram, and the Lomb-Scargle periodogram},
  author = {Barry G. Quinn},
  booktitle = {ICASSP 2016},
  year = {2016}
}