search

franzmohr / bvartools

Functions for Bayesian inference of vector autoregressive and vector error correction models
30 stars 11 forks source link

Question about "new_d" argument in "predict" #4

Closed RightHandOfDoom closed 1 year ago

RightHandOfDoom commented 1 year ago

Hello! I have a question about the "new_d" argument in the "predict()" function. The example is unfortunately not very clear to me. The example dataset e1 has three variables (invest, income, cons) but "new_d" has only one row. How can the function identify for which variable this vector represents deterministic terms? What if, for example I wanted to provide 10 new datapoints for "income", while predicting the other two variables? What if I have data for both cons and income, for example? How would I have to change the argument "new_d" in this case? I hope my understanding is not too wrong. Thank you very much for your help!

franzmohr commented 1 year ago

Hi! Sorry for the late response. new_d is for deterministic variables only, as new_x is only for other exogenous variables. Unfortunatly, the function does not support overwriting endogeneous variables yet, but I will try to accomodate this in the future. Best Franz