I would like to retrieve the simulated series of endogenous variables after I have performed bayesian estimation. I have 4 series: inflation, output gap, interest rates and stock prices. I tried to use the stoch_simul (periods = integer) command after estimation and then compared the simulated variables to actual data. The result is very obscure. The series are not even close.
Can anyone help?
You mean that when you plot them, they are not similar at all?
No, not at all. I was hoping that the simulations would closely follow the path of actual variables.
If these are series that you have used in estimation (i. e. observed variables), use simply command filtered_vars which plots estimated variables using one-sided Kalman filter. The Kalman filter estimates of the observed variables can be given the same interpretation as the fitted values of a regression.
estimation (datafile=?, …,** filtered_vars**, …)
Thanks for the suggestion. I tried to look at the plot of the actual vs filtered variables. The filtered variables almost look like the smoothed/updated varibales. I was hoping I could get the simulated variables. Any suggestions?