Question about observation equation and data dealing

This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location where you will have to reset your password.
Forum rules
This forum is closed. You can read the posts but cannot write. We have migrated the forum to a new location (https://forum.dynare.org) where you will have to reset your password.

Question about observation equation and data dealing

Postby lssp » Wed Dec 17, 2014 12:57 am

Hi, Professor Pfeifer,

I have a question about the observation equation after I have red your paper "A Guide to Specifying Observation Equations for the Estimation of DSGE Models".
Would you please help me ?

Q1:
The model I am dealing with (as attached ) is a nonlinear model, but the Taylor Rule is linear form, like:

ReXU = rhotilUU*ReXU(-1) + (1-rhotilUU)*(ReXUU+aptilUU*(piU(+1)-piUU)+aytilUU*(YU-YUU)) + e_xpU;
e_xpU=rho_m*e_xpU(-1)+em;

em is the shock.

If I want to do the estimation using the data of ReXU, how should I write the correct observation equation ? and how to deal with the raw data ?

Q2:
when I want to add a technological shock and its AR(1) process into the model, like:

YU - AU* ((KtotU^alphaUU)*(hU ^(1-alphaUU)) ) ;
log(AU) = rho_A*log(AU(-1))+eA;

Then the rank condition isn't verified. What happen ? How to solve this problem ?

I am looking forward to your reply,
thank you very much!
Last edited by lssp on Sat Jan 03, 2015 1:49 am, edited 1 time in total.
lssp
 
Posts: 15
Joined: Thu Apr 10, 2014 12:22 pm

Re: Question about observation equation and data dealing

Postby jpfeifer » Thu Dec 18, 2014 4:52 pm

1) You need to match ReXU to the data. ReXU is the log deviation of the quarterly gross nominal interest from its mean. Thus, just follow the advice in my Guide to compute this observable. For the purpose of this observed variable, the treatment is exactly the same for a loglinearized model, because this variable is loglinearized. You just need to make sure that in other equations you remember that ReXU is a log-deviation and not a level. Currently, you seem to only take the log of the interest rate, but not the devation from the mean of log interest rate
2) I cannot replicate this issue. When I add that shock, there is no singularity.


Finally, your estimation routine looks incorrect due the steady state not being correctly updated. After running estimation, Dynare will update the estimated parameters but not take any dependence into account that you did not specify. Rather, your calibration only once updates the other parameters depending on the estimated one. That’s why you should use model-local variables (the ones with the pound operator) or a steady state file. See Remark 4 (Parameter dependence and the use of model-local variables) in Pfeifer(2013): "A Guide to Specifying Observation Equations for the Estimation of DSGE Models" https://sites.google.com/site/pfeiferecon/Pfeifer_2013_Observation_Equations.pdf.
------------
Johannes Pfeifer
University of Cologne
https://sites.google.com/site/pfeiferecon/
jpfeifer
 
Posts: 6940
Joined: Sun Feb 21, 2010 4:02 pm
Location: Cologne, Germany

Re: Question about observation equation and data dealing

Postby chenp2002 » Sat Jun 24, 2017 5:01 pm

Dear Mr jpfeifer:
In china,we can not use the google.cn,so i can not down your file,https://sites.google.com/site/pfeiferecon/Pfeifer_2013_Observation_Equations.pdf.do you have another place to download,or if possible,could you send the file to my email,chenp2002@126.com,thank you very much.
chenp2002
 
Posts: 10
Joined: Thu Jun 22, 2017 8:34 am

Re: Question about observation equation and data dealing

Postby jpfeifer » Sun Jun 25, 2017 8:37 am

I sent it via Email
------------
Johannes Pfeifer
University of Cologne
https://sites.google.com/site/pfeiferecon/
jpfeifer
 
Posts: 6940
Joined: Sun Feb 21, 2010 4:02 pm
Location: Cologne, Germany


Return to Dynare help

Who is online

Users browsing this forum: No registered users and 5 guests