How to do ardl using eviews?

[Milk88]

Dear all, i have few questions regarding doing ardl in eviews. I never learn ardl before but my supervisor ask me to apply ardl in my thesis and ask me to learn myself. I have limited knowledge about ardl. I have done my unit root test and confirm all my variables are I(0) or I(1). As i watched from other source (like youtube), is it the next step is to form an equation? How to form that equation? And i saw the equation come with lag in the brackets. How to determinate what lag for each variable. My data is annually, My dependent variable is lfdi, independent variables are lgdp, lgfcf, lci, lfx, lopen. Hope someone can answer my question. Really appreciate~

[EViews Gareth]

http://davegiles.blogspot.ca/2013/03/ar ... art-i.html

[Milk88]

hii, thanks for the reply. but the link shown doesnt explain how to choose the lag, and how to form the equation in eviews. As what i can see from other sources, the equation is something like "d(lnip) lnip(-1) lnrop(-1) lnex(-1) lncpi(-1) d(lnip(-1)) d(lnip(-2)) d(lnip(-3)) d(lnip(-4)) d(lnip(-5))..." copy form somewhere.

[BobJ]

Is there any reason why you can't use the information criteria to pick lag length? I would think the AIC or BIC would work fine.

[hossein khandani]

.........

[hossein khandani]

example

[EViews Glenn]

http://davegiles.blogspot.ca/2015/01/ar ... ews-9.html

[econworker]

Dear Hossein, many thanks for sharing the codes of panel ARDL, however, I am interested to know that is this the same method of PMG estimator which is proposed by Pesaran et al (1997)?
Thanks in advance

ARDL PANEL:

Edited by hossein khandani

for:
POOL

fixed effects

Random effects

[hossein khandani]

Dear Hossein, many thanks for sharing the codes of panel ARDL, however, I am interested to know that is this the same method of PMG estimator which is proposed by Pesaran et al (1997)?
Thanks in advance



NO, maybe dfe

All parameters, except intercepts, are constrained to be equal across panels



homogeneous panels

ARDL PANEL:

Edited by hossein khandani

for:
POOL

fixed effects

Random effects

[econworker]

Dear Hossein, many thanks for sharing the codes of panel ARDL, however, I am interested to know that is this the same method of PMG estimator which is proposed by Pesaran et al (1997)?
Thanks in advance



NO, maybe dfe

All parameters, except intercepts, are constrained to be equal across panels

Thanks for your reply, I used the codes, after generating the results I would say that I have serious doubts if this is a panel ARDL estimation, specifically the table of ARDL results, an ARDL model should takes the first difference of the dependant variable as a function of the first lag of level of itself and the level of all independant variable as well as the first difference of all independant variables using different lag orders as suggested by criteria, however, the results of your provided codes generates a simple panel estimation not an ARDL.


homogeneous panels

ARDL PANEL:

Edited by hossein khandani

for:
POOL

fixed effects

Random effects