Simultaneous Equation with non-observable variable

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

ys1980
Posts: 3
Joined: Tue Dec 28, 2010 2:53 am

Simultaneous Equation with non-observable variable

Postby ys1980 » Tue Dec 28, 2010 3:13 am

I have 2 independent variables (assume R1 R2, respectively) which are my sample data.
I want to estimate simultaneously 3 equations as follows (the 3th variable called R3 is non-observable):
Log(R3)=c(1)*R3(-1)+ c(2)*R3(-2)+ c(3)*R3(-3)
R1=c(4)*R3+c(5)*resid(-1)
R2=c(6)*R3+c(6)*resid(-1)

1.How can I run these equations at eviews?
2.How can I define the residual for each equation (in my question, there are to residual derive from each equation?

Thanks

trubador
Did you use forum search?
Posts: 1520
Joined: Thu Nov 20, 2008 12:04 pm

Re: Simultaneous Equation with non-observable variable

Postby trubador » Tue Dec 28, 2010 6:56 am

1.How can I run these equations at eviews?
You can use "State Space Object". R1 and R2 are your signal variables, whereas R3 is your state variable. Please see the manual for details.
2.How can I define the residual for each equation (in my question, there are to residual derive from each equation?

Code: Select all

eq1.makeresids res1 eq2.makeresids res2

ys1980
Posts: 3
Joined: Tue Dec 28, 2010 2:53 am

Re: Simultaneous Equation with non-observable variable

Postby ys1980 » Tue Dec 28, 2010 7:26 am

can you please write me down the code for these equations?
where do I need to write it? should I need to create 3 equations?

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Simultaneous Equation with non-observable variable

Postby startz » Tue Dec 28, 2010 7:47 am

1. You should begin by taking a look at Chapter 33 of the online user's guide.
2. Are you sure you've read your homework assignment correctly? Those are odd looking equations unless there is more information that you've left out.

ys1980
Posts: 3
Joined: Tue Dec 28, 2010 2:53 am

Re: Simultaneous Equation with non-observable variable

Postby ys1980 » Tue Dec 28, 2010 8:09 am

this is a part of leading indicator model which is quite difficult to understand, it's not homework

startz
Non-normality and collinearity are NOT problems!
Posts: 3797
Joined: Wed Sep 17, 2008 2:25 pm

Re: Simultaneous Equation with non-observable variable

Postby startz » Tue Dec 28, 2010 8:29 am

The model appears to not be identified, unless there are some further conditions. Suppose all R3 doubled and c(3) and c(4) were cut in half.


Return to “Estimation”

Who is online

Users browsing this forum: No registered users and 2 guests