Hello,
I am interested in the estimation of Taylor rule with interest rate smoothing, like in the attached picture.
I have done only simple regressions, but I have never done regression with rho(smoothing parameter).
Can anyone suggest how it can be done in EViews?
Thank you in advance!
Estimation of Taylor rule with smoothing parameter
Moderators: EViews Gareth, EViews Moderator

 Nonnormality and collinearity are NOT problems!
 Posts: 3376
 Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation of Taylor rule with smoothing parameter
You can specify a regression in EViews by writing out an equation using c(1), c(2), etc as names for the coefficients, as in
Code: Select all
ls y=c(1)*c(2) + c(2)*x
Re: Estimation of Taylor rule with smoothing parameter
Thank you for your reply.
I now understand that I porbably need to do this regression with GMM method, I specified everything, but something is wrong as I get message singular matrix. How can I fix this?
I now understand that I porbably need to do this regression with GMM method, I specified everything, but something is wrong as I get message singular matrix. How can I fix this?
 Attachments

 Screenshot (2).png (10.63 KiB) Viewed 424 times

 Nonnormality and collinearity are NOT problems!
 Posts: 3376
 Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation of Taylor rule with smoothing parameter
I think that the problem is that you have both included c and clicked include a constant in the instrument list.
Re: Estimation of Taylor rule with smoothing parameter
I deleted c from the instrumental list, but it still does not work and I get message singular matrix. Maybe you have other ideas?
I am so desperate, don't know how to solve this problem.
I am so desperate, don't know how to solve this problem.

 Nonnormality and collinearity are NOT problems!
 Posts: 3376
 Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation of Taylor rule with smoothing parameter
What you've done looks right. Since your model is linear, you might try the TSLS command and see if that works. Also, before you run GMM set c=0.
Re: Estimation of Taylor rule with smoothing parameter
What do you mean by set c=0? How can I do that? Will it impact results?
Thank you in advance!
Thank you in advance!

 Nonnormality and collinearity are NOT problems!
 Posts: 3376
 Joined: Wed Sep 17, 2008 2:25 pm
Re: Estimation of Taylor rule with smoothing parameter
Type c=0 into the command line before estimating an equation. This resets the starting values of the coefficients. Not likely to matter, but there's a chance.
Re: Estimation of Taylor rule with smoothing parameter
It still does not work.
Tried to do the same way as in this pdf http://coin.wne.uw.edu.pl/~lgoczek/pdf/ ... trics5.pdf, but no results.
The problem only disappears when I remove a constant term c(2) from the regression, but I cannot use such result, I think.
Anyway, thank you for your help and time, I really appreciate that!
Tried to do the same way as in this pdf http://coin.wne.uw.edu.pl/~lgoczek/pdf/ ... trics5.pdf, but no results.
The problem only disappears when I remove a constant term c(2) from the regression, but I cannot use such result, I think.
Anyway, thank you for your help and time, I really appreciate that!
Who is online
Users browsing this forum: No registered users and 9 guests