Ah! Yes, indeed, this was at ENSAE and you could have guessed Christian Gouréroux was the lecturer then!

]]>The information content is the same, since the finite Fourier transform is invertible. Another way to look at it is that it’s really a lot like Principal Component Analysis, in that it produces uncorrellated variables from correlated variables by applying a linear transformation.

]]>This is a very helpful reason for turning to the frequency domain, then. Would it make any sense to compare the information contents of time domain and frequency domain representations of a dataset?

]]>* See Harvey, A. C. and Jaeger, A. (1993), Detrending, stylized facts and the business cycle. Journal of Applied Econometrics, 8: 231–247 which I summarize in my blog.

]]>