Hi all,
I'm trying to use gretl's vecm command to estimate asymetry price transmission as
:
Long -run dynamic
LogPR(Retail price)=alpha+ beta *logPP(Producer price)
Short-run dynamic
d_logPR (Retail price ) = d_logPR (Retail price )(-1) + d_logPR (Retail price )(-2)
+d_logPP (Producer price )(-1) +... Z-plus + Zminus
with
Z-plus = I* (LogPR- alpha- Beta*LogPP)
Z-minus = (1-I)* (LogPR- alpha- Beta*LogPP)
I= 1 when d_u(t-1) >=0 and 0 Otherwise
Does anyone here have a best way to address this? Thanks!
Help is much appreciated!
--------------------------------------------
Dr.Ali Ferjani
Sozioökonomie
Eidgenössisches Volkswirtschaftsdepartement EVD
Forschungsanstalt Agroscope Reckenholz-Tänikon ART
Federal Department of Economic Affairs DFE
Agroscope Reckenholz-Tänikon Research Station ART
Tänikon, CH-8356 Ettenhausen
Tel. 052 368 32 75
Fax 052 365 11 90
ali.ferjani(a)art.admin.ch
www.art.admin.ch
-------------------------------------------
-----Ursprüngliche Nachricht-----
Von: gretl-users-bounces(a)lists.wfu.edu
[mailto:gretl-users-bounces@lists.wfu.edu]Im Auftrag von
Allin Cottrell
Gesendet: Freitag, 4. Juli 2008 14:43
An: Gretl list
Betreff: [Gretl-users] handling of session models unstable
A brief warning on the current state of gretl CVS: I'm trying to
make it so that models estimated via the GUI menus, and then
saved, are treated in the same way as models saved by the script
mechanism, as for example
Model_name <- ols y 0 xlist
However, I noticed today that my work on this has broken the
handling of models saved in session files: you are likely to get
memory corruption on exiting gretl when such models are freed.
I'll try to fix this by tomorrow.
Allin Cottrell
_______________________________________________
Gretl-users mailing list
Gretl-users(a)lists.wfu.edu
http://lists.wfu.edu/mailman/listinfo/gretl-users