Navigation:  Menu Commands > Tools Menu >

 

Monte Carlo Filtering

 

Print this Topic Previous pageReturn to chapter overviewNext page

The Monte Carlo filtering function relies on a large number of draws from the prior distribution. For each draw the DSGE model solution properties are checked and organized into three categories: (1) a unique and stable (convergent) solution; (2) indeterminacy; and (3) no stable solution.

The function computes Kolmogorov-Smirnov tests for each estimated parameter of the hypothesis that the distributions are the same for case (1) and cases (2) & (3). It is also possible to scatter plot pairs of parameters with each dot colored by its model solution property. The Monte Carlo filtering approach has been suggested in Ratto (2008).

 

Additional Information

A more detailed description about the Monte Carlo filtering can also be found in Section 11.14 of the YADA Manual.

 

 


Page url: http://www.texlips.net/yada/help/index.html?monte_carlo_filtering.htm