Dynamic factor model SS

For technical questions regarding estimation of single equations, systems, VARs, Factor analysis and State Space Models in EViews. General econometric questions and advice should go in the Econometric Discussions forum.

Moderators: EViews Gareth, EViews Moderator

xychen1
Posts: 7
Joined: Tue Aug 14, 2012 12:26 am

Dynamic factor model SS

Postby xychen1 » Wed Mar 20, 2013 11:14 am

Hi,
I am writing a code for a simple dynamic factor model. I am trying to extract mom gdp growth based on a factor called f1. For the moment, we can treat f1 as exogeneous. The equations I am trying to achieve is,

y(q) = 1/3 * y(t) + 2/3 * y(t-1) + y(t-2) + 2/3 * y(t-3) + 1/3 * y(t-4)
y(t) = c(1) * f1 + e1


-y(q) is in quarterly basis.

The code I wrote is.
@signal gdp2 =1/3* sv1 + 2/3 * sv2 + sv3 + 2/3 * sv4 +1/3 *sv4(-1)
@signal l_factor = c(1) * sv1 + [var = exp(c(1))]
@state sv2 = sv1(-1)
@state sv3 = sv2(-1)
@state sv4 = sv3(-1)

for some reason i kept getting an error msg, " syntax error in equation in equation @signal gdp2 =c(1) * sv1 + c(2) * sv2 + c(3) * sv3 + * sv4 +1/3 *sv4(-1)


Can someone kindly point out how i can rectify this error?
thanks!

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: Dynamic factor model SS

Postby startz » Wed Mar 20, 2013 11:33 am

Lags of state variables, sv4(-1), aren't allowed.

xychen1
Posts: 7
Joined: Tue Aug 14, 2012 12:26 am

Re: Dynamic factor model SS

Postby xychen1 » Wed Mar 20, 2013 11:40 am

no, i've allowed a sv5 = sv4(-1)
still not working. any other suggestion?

startz
Non-normality and collinearity are NOT problems!
Posts: 3798
Joined: Wed Sep 17, 2008 2:25 pm

Re: Dynamic factor model SS

Postby startz » Wed Mar 20, 2013 11:47 am

You're not showing a state equation for sv1.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests