Dealing with bad/unobservable data

How does one deal with bad/unobservable data? For example, in Smets-Wouters (2003), the authors said “as we do not have good measures of the area-wide capital stock, the value of capital or the rental rate on capital, we will assume these variables are not observed”. Similarly, my problems is that I have a bad real wage data, which I want to treat as unobservable. So how does one goes about that? How does one estimate/do it in dynare? any reference/readings you can recommend on the actual estimation implementation (I know in principle it is possible in Bayesian estimation, but my question goes more on actual (Dynare) estimation, step by step.)

Thank you in advance for any help/recommendation!


if your wage series r not good enough such as you don’t wanna use them as observable, just don’t specify in Dynare the wage variable in the instruction "varobs ;"
Sometimes there might be a way to use this information by introduced a measurement equation in the block “model” and as far as I remember thats what SW(2003) did
with employment (due to missing values issue)…

Hope this helps

Hi, thank you for the reply.
Just a little follow up – sorry I am new to Dynare. So, how do I tell Dynare: estimate the unobservable wage data? Or how do I tell dynare: ok, my model includes real wage, but you have to estimate the model without the data (on real wage) – what do I write in the instructions? I would appreciate details – step by step explanation – thank you!

does anybody have the Smets-Wouters 2003 code and data by the way? (I have the SW AER 2007). Thanks again!

Dear Pert,
I think you should read the Dynare documentation more carefully.

Regarding the Smets-Wouters 2003 code. You can search for “Smets” in this forum and you will find some posts regarding the 2003 version of the code. You can contact those people directly - they should probably have the code.