Help DSGE-VAR model.

[georgezt]

Hi

We are trying to analysis the Chinese monetary policy with the DSGE-VAR Model , we now apply the model in the paper of Del Negro, M., and F. Schorfheide (2004). And the code is from Prof. Stephane. But i have the error in the process, the error is as follows

Starting MATLAB/Octave computing.

Loading 52 observations from zhw.xls

Loading 52 observations from zhw.xls

VarSampleMoments :: not enough data to initialize! Try to increase FirstObservation.

as i know, the DSGE_VAR model will generate observations from the dsge model, so I think it will always have the enough data

Another question is that how to determine the number of lags of the VAR, should we determine the lags in advance with some tests or the model can

determine the lags itself ?

the attachments are the data and code

Thanks a lot

George.Z Shi.C

[StephaneAdjemian]

Hi,

The DSGE-VAR(p) model is a BVAR(p) model with a prior (for the autoregressive matrices of the VAR) defined by a DSGE model. To evaluate the (conditional) likelihood of any VAR model you need initial conditions: p initial conditions for a VAR(p). You should read more carefully the paper by Del Negro and Schorfheide or this page on our wiki (in particular the expression of the posterior density, equations Q in the wiki page, where the sample autocovariance function of the observed variables appears).

Best,
Stéphane.