1:33 a.m.
Hello all,
Up till now, gretl has supported only three-stage least squares for
estimating systems of simultaneous equations. Now, in CVS and in
the win32 snapshot available from sourceforge, I have added support
for FIML and LIML (along with automatic testing of over-identifying
restrictions). I have also added the Hansen-Sargan test for
over-identifying restrictions, for 3SLS and SUR.
I'm looking for help in testing these new additions. I can
replicate the benchmark results for that workhorse, Klein's "Model
1", but I'm finding it hard to find other benchmarks to test
against. So if anyone has datasets on which they've estimated
equation systems using FIML or LIML with other programs, I'd be very
grateful if you could either:
* See if you can replicate the results using gretl, and let me know
what happens; or
* Send me a copy of the dataset and the output from the other
program, so I can try the replication.
Thanks very much for any assistance.
--
Allin Cottrell
Department of Economics
Wake Forest University, NC
2:26 a.m.
New subject: simultaneous equations in gretl [2]
Sorry, I forgot to mention: I have revamped the "system" command and
added a new command, "estimate", so that one can define an equation
system then estimate it using various methods.
I'm attaching the latest revision of the gretl demo file klein.inp,
which provides an example of how this works.
--
Allin Cottrell
Department of Economics
Wake Forest University, NC
1:03 p.m.
New subject: simultaneous equations in gretl [2]
Impressive.
Thanks,
Wilson Mixon
Allin Cottrell wrote:
Sorry, I forgot to mention: I have revamped the "system"
command and
added a new command, "estimate", so that one can define an equation
system then estimate it using various methods.
I'm attaching the latest revision of the gretl demo file klein.inp,
which provides an example of how this works.
------------------------------------------------------------------------
# Klein's "Model 1" (1950)
open klein.gdt
genr W = Wp + Wg
genr A = t - 1931
genr P1 = P(-1)
genr X1 = X(-1)
# Equation-by-equation OLS
ols C 0 P P1 W
ols I 0 P P1 K1
ols Wp 0 X X1 A
# Equation-by-equation TSLS
tsls C 0 P P1 W ; 0 G T A Wg P1 K1 X1
tsls I 0 P P1 K1 ; 0 G T A Wg P1 K1 X1
tsls Wp 0 X X1 A ; 0 G T A Wg P1 K1 X1
# Now set the model up as a system
system name="Klein Model 1"
equation C 0 P P1 W
equation I 0 P P1 K1
equation Wp 0 X X1 A
identity P = X - T - Wp
identity W = Wp + Wg
identity X = C + I + G
endog C I Wp P W X
end system
# and estimate it in various ways
estimate "Klein Model 1" method=3sls
estimate "Klein Model 1" method=fiml
estimate "Klein Model 1" method=liml
------------------------------------------------------------------------
_______________________________________________
Gretl-users mailing list
Gretl-users(a)ricardo.ecn.wfu.edu
http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users
5:34 p.m.
New subject: simultaneous equations in gretl [2]
Allin:
I was cleaning up my email and ran across this exchange. Since you told
me about this, I have been using various combinations of system,
restrict, and coeffsum to very good effect. GRETL just continues to impress!
Wilson
Wilson Mixon wrote:
Impressive.
Thanks,
Wilson Mixon
Allin Cottrell wrote:
> Sorry, I forgot to mention: I have revamped the "system" command and
> added a new command, "estimate", so that one can define an equation
> system then estimate it using various methods.
>
> I'm attaching the latest revision of the gretl demo file klein.inp,
> which provides an example of how this works.
>
> ------------------------------------------------------------------------
>
> # Klein's "Model 1" (1950)
> open klein.gdt
> genr W = Wp + Wg
> genr A = t - 1931
> genr P1 = P(-1)
> genr X1 = X(-1)
> # Equation-by-equation OLS
> ols C 0 P P1 W ols I 0 P P1 K1
> ols Wp 0 X X1 A
> # Equation-by-equation TSLS
> tsls C 0 P P1 W ; 0 G T A Wg P1 K1 X1
> tsls I 0 P P1 K1 ; 0 G T A Wg P1 K1 X1
> tsls Wp 0 X X1 A ; 0 G T A Wg P1 K1 X1
> # Now set the model up as a system
> system name="Klein Model 1"
> equation C 0 P P1 W equation I 0 P P1 K1
> equation Wp 0 X X1 A
> identity P = X - T - Wp
> identity W = Wp + Wg
> identity X = C + I + G
> endog C I Wp P W X
> end system
> # and estimate it in various ways
> estimate "Klein Model 1" method=3sls
> estimate "Klein Model 1" method=fiml
> estimate "Klein Model 1" method=liml
>
>
>
>
> ------------------------------------------------------------------------
>
> _______________________________________________
> Gretl-users mailing list
> Gretl-users(a)ricardo.ecn.wfu.edu
> http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users
>
>
_______________________________________________
Gretl-users mailing list
Gretl-users(a)ricardo.ecn.wfu.edu
http://ricardo.ecn.wfu.edu/mailman/listinfo/gretl-users
1:05 a.m.
New subject: simultaneous equations in gretl [2]
On Sat, 13 Aug 2005, Wilson Mixon wrote:
I was cleaning up my email and ran across this exchange. Since you
told me about this, I have been using various combinations of
system, restrict, and coeffsum to very good effect. GRETL just
continues to impress!
Glad you like it! There is more good stuff on the way in the next
gretl release (mostly in respect of vector analysis of time series
data).
Allin.
7055
days inactive
7304
days old
4 comments
2 participants
participants (2)
-
Allin Cottrell -
Wilson Mixon