Mode plot (interpretation)

[ManuelTorres]

Hi everyone, hi Dr. Pfeifer,

I have observed in this forum that the command mode_check serves to identify problems with the parameters of the model, in particular, if the log-likelihood function is flat, we can say that there is an identification problem (correct me if not).
I use the command to see what happened to the parameters of my model, apparently they all behave well, (except varrhoI) however, there are some that are flat and suddenly have peaks (rhoi) or there are some that seem to have volatility (varrhoW), and I would like to know if this is telling me something or just that my parameters are not entirely flat.

I attach the graphs

[jpfeifer]

See

Some questions about identification

You are neglecting the different scale in the mode_check-plot. The likelihood line is the green line at the top of the figure that merges with the boundary of the subplot. It is the massively informative prior that gives the blue line the shape. Regarding the interpretation of the identification strength graph, please see Pfeifer (2014): “An Introduction to Graphs in Dynare” at sites.google.com/site/pfeiferecon/dynare. The identification strength is generally evaluate for the posterior with Ba…

You should look at the scaling of both the x- and y-axis. For varrrhoW you are at the boundary to 1, i.e. at a corner solution.