Hello, I have the following problem:
Suppose that I estimate the spectral density of some weakly stationary process nonparametrically, say by smoothing the periodogram. Is there a simple way to recover the coefficients of the wold representation of the process (i.e. infinite moving average representation). Better yet, can I infer the asymptotic standard errors of the Wold coefficients from that of the spectral density at different frequencies?
I have this problem in my research and would greatly appreciate any comment you may have.