I am working on a signal processing lecture for undergraduate students with Mathematica exercises/examples, and I would like to explain to them what happens when they run the PowerSpectralDensity[data,...] function. It returns a linear combination of cosines, so I suspect that maybe a linear regression is used behind the scenes (which is one of the well-known ways of constructing periodograms), but it would be nice to know for sure. Any hints would be much appreciated.


closed as off-topic by Szabolcs, corey979, Edmund, MarcoB, m_goldberg Apr 13 at 4:01

This question appears to be off-topic. The users who voted to close gave this specific reason:

  • "This question arises due to a simple mistake such as a trivial syntax error, incorrect capitalization, spelling mistake, or other typographical error and is unlikely to help any future visitors, or else it is easily found in the documentation." – Szabolcs, corey979, Edmund, MarcoB
If this question can be reworded to fit the rules in the help center, please edit the question.

  • 1
    $\begingroup$ Have you looked at the Details and Options of PowerSpectralDensity? $\endgroup$ – corey979 Apr 12 at 11:25
  • $\begingroup$ Voting to close as "easily found in documentation", as it seems to be explained there. If you disagree, please clarify. $\endgroup$ – Szabolcs Apr 12 at 11:43
  • 3
    $\begingroup$ Generally, for "how does it work" questions, I suggest the following steps (in order): 1. Check the function's documentation page. Always check carefully under the Details and in the Background section. 2. See if there are advanced tutorials (always check the Related Tutorials and do an additional search) E.g. NDSolve, NDSolve and GraphPlot have advanced tutorials which detail the methods they use 3. Check here: reference.wolfram.com/language/tutorial/… 4. Search StackExchange 5. If still no luck, write to Wolfram Support $\endgroup$ – Szabolcs Apr 12 at 11:46
  • $\begingroup$ @corey979 Yes, I did check the "Details and Options". Looks like they Fourier-transform the empirical covariance function, Wiener-Khinchin-theorem-style. Which is bad for my lecture because I want to introduce that topic "independently". $\endgroup$ – Laryx Decidua Apr 12 at 13:35