search

CPCLAB-UNIPI / SIPPY

Systems Identification Package for PYthon
GNU Lesser General Public License v3.0
269 stars 92 forks source link

Question about how to perform k-step ahead prediction #9

Open vickysun5 opened 5 years ago

vickysun5 commented 5 years ago

Hi, I wonder how can I do the k-step ahead prediction after I fitted the system. (For example, I have a test data set and I want to use the model to do 1-step and 2-step prediction to see how it performs).

Moreover, what is the difference between the simulation and prediction modes? I am new to this filed and really appreciate your answer!

CPCLAB-UNIPI commented 5 years ago

Dear vickysun5,

at the present, SIPPY does not implement a function to perform k-step ahead prediction. Your issue is very interesting and we may consider to include this possibility in a future release.

In the identification routine, the prediction error is now calculated as the difference between the actual output and its one-step ahead prediction, e.g., all the the previous outputs, depending on the model order, are used to build the current output.

Hoping to have answered your questions. Do not hesitate to contact us for any additional doubts.

Best