I am trying to find any guides on how to use Kalman filters with ARIMA models but the only sources I have found have been highly technical that I can't really understand. Can anyone point me towards tutorials or books that might be friendlier to a beginner?
$\begingroup$
$\endgroup$
1
asked Dec 17, 2020 at 1:41
-
$\begingroup$ youtube.com/watch?v=CaCcOwJPytQ $\endgroup$– DaveCommented Dec 23, 2020 at 13:27
Add a comment
|
2 Answers
$\begingroup$
$\endgroup$
1
Unfortunately, the Kalman filter methodology is a fairly advanced topic in econometrics, hence it is quite difficult to find simple examples, both because it is a complex topic that requires a deeper knowledge of the maths behind it, and because it is easier to make tutorials of simple things.
However, here you can find a quite simple example by Maitra, "State Space Model and Kalman Filter for Prediction" in R on Kalman filter for DLM, that is a generalization of ARIMA with external regressors.
Nevertheless, since you are interested in time series forecasting and estimation, I suggest you to look at the forecast package in R by Professor Rob J. Hyndman (there should also be a Python version), that allows to estimate various time series models in state-space forms, and maybe the book "Forecasting: Principles and Practice" by Rob J. Hyndman and George Athanasopoulos.
-
$\begingroup$ Including a full title in case the link goes dead is an encouraged practice. $\endgroup$ Commented Dec 23, 2020 at 13:31
$\begingroup$
$\endgroup$
The best I found till now is this open source interactive book: Kalman and Bayesian Filters in Python
Hope this helps !
