The RATS Software Forum

Hi Tom, sorry to bother again, but I wonder if it would be possible to use EM to estimate MS-VAR model and apply MCMC to construct impulse responses' confidence intervals, if the answer is yes, could you provide a hint (which part of the code to look at) how to do so?

Hi Tom I realized that the EM version is more suitable for my research, because it allows me to do the specification test while the Bayesian method doesn't (correct me if I wrong). Moreover, I am not really a Bayesian person so it would take me quite a while to understand its background if I choose ...

Dear Tom, I have estimated the model with EM method, now I need to compute the confidence bands for the IRF. It seems that it is possible to obtain the bands using MCMC method, as the following paper has done: http://web.up.ac.za/sitefiles/file/40/677/WP_2012_22.pdf Would you please provide any clue...

SWITCH =[C]/CH/H C means that coefficients are switching, H indicates variances are switching. NFIX =# of explanatory variables which are fixed across regimes [0 or all] If SWITCH=C or CH, the default is 0, if SWITCH=H, it's all. The fixed coefficients must be placed first in the supplementary card...