I have estimated AR coefficients of a time series using "aryule" function in MATLAB. Now I want to obtain the error of the estimated model. I think at first I must reconstruct it. so How can I reconstruct a Time series using it AR coefficients in MATLAB?
$\begingroup$
$\endgroup$
2
-
1$\begingroup$ What do you mean by the "error of the estimated model" ? Do you know the true coefficients that were used to generate the original time series? $\endgroup$– Peter K. ♦Jan 8, 2016 at 19:38
-
$\begingroup$ Use Least square method (LS) Hope that help $\endgroup$– NasrNov 24, 2017 at 14:29
Add a comment
|
1 Answer
$\begingroup$
$\endgroup$
If you drive your AR model with white noise, you can generate a time series that has the same power spectral density as the original time series. But it won't be the same time series.