Am 11.03.2024 um 11:52 schrieb Dionysio
Lalounta:

Hi all, I have a few questions about BVAR package . At first how can I save the forecasted values of the depedent variables , in order to calculate RMSE etc?

This should probably be mentioned or explained in the manual, admittedly. Right now the idea is that you use the built-in plotting functions.

Anyway, please grab the result bundle from BVAR_posterior (in your example below, "res1"), and then check out the sub-bundle "fcast". In there you find a matrix for each endogenous variable. The column labels should hopefully be self-explanatory. Please bear in mind that the Bayesian approach produces densities, it's not clear a priori what _the_ (point or path) forecast is.

The second question is about the inclusion of exogenous vars in the model . I wrote the following script clear --dataset # read data available up to 2023:4 open dbnomics data Eurostat/namq_10_gdp/Q.CLV05_MEUR.SCA.B1GQ.EA --name="YER" data Eurostat/namq_10_gdp/Q.PD05_EUR.SCA.B1GQ.EA --name="YED" data ECB/FM/Q.U2.EUR.RT.MM.EURIBOR1MD_.HSTA --name="STN" data ECB/FM/Q.U2.EUR.4F.CY.OILBRNI.HSTA --name="POILU" # BVAR with exogenous vars list POILU1 =POILU # create a list for the exogenous variable series yer=100*ldiff(YER) series yed =100*ldiff(YED) list dep = yer yed STN # create list for endogenous vars lag =4 type ="fixed" # minnesota exog = POILU1 bundle mod1 = BVAR_setup(dep, lag, type,_(exog=POILU1)) # bundle with exogenous variable matrix m= zeros(1,4) m={80,85,80,86} #future values for exogenous var smpl 2000:1 2022:4 bundle res1 = BVAR_posterior(mod1,"all",_(iter = 10000, fcast_h = 4,fcast_exog=m)) # with exogenous var When run the above script I get the following error #ERROR MESSAGE #error! Provide fcast_h obs of exog (as matrix, rows) for fcast!

It looks as if your m matrix is a row vector, but you need a column vector as suggested in the error message (obs in rows).

thanks for using and testing the BVAR package

Sven