HI,
I am trying to estimate a panel cointegration model and save the individual coefficients in a matrix. I use the command as specified in the guide (btwcoefs=) and it works for when using grouped panel method, but not for the other two (see below). Is there a reason for that or is it a bug?
dols_prod.cointreg(method=dols, btwcoefs=zpr,lltype=sic, panmethod=grouped) y x z
dols_prod.cointreg(method=dols, btwcoefs=zpr,lltype=sic, panmethod=pooled) y x z
dols_prod.cointreg(method=dols, btwcoefs=zpr,lltype=sic, panmethod=weighted) y x z
Kind regards,
Marta
Individual coefficients in Panel cointegration not saved with btwcoefs
Moderators: EViews Gareth, EViews Jason, EViews Moderator, EViews Matt
-
- EViews Developer
- Posts: 2672
- Joined: Wed Oct 15, 2008 9:17 am
Re: Individual coefficients in Panel cointegration not saved with btwcoefs
Sorry, the documentation is unclear (that one is my fault).
The cross-section coefficients were designed to be saved only in the case where you are estimating the between (grouped) model in a panel context (panmethod=grouped), as that is the only time that they are calculated explicitly. So the two options should have been listed under Panel Options, and have a note, only if “panmethod=grouped”.
That said, we are currently displaying estimates of the individual deterministics in the other two cases and I’ll have to look into why we aren’t allowing you to save them (we added that feature after the initial release). Note that we will never save the covariance for these estimates as they are treated as nuisance parameters and never estimated. We'll look into it for a future version, but for now, all you can do is copy the results from the individual coefficients view.
The cross-section coefficients were designed to be saved only in the case where you are estimating the between (grouped) model in a panel context (panmethod=grouped), as that is the only time that they are calculated explicitly. So the two options should have been listed under Panel Options, and have a note, only if “panmethod=grouped”.
That said, we are currently displaying estimates of the individual deterministics in the other two cases and I’ll have to look into why we aren’t allowing you to save them (we added that feature after the initial release). Note that we will never save the covariance for these estimates as they are treated as nuisance parameters and never estimated. We'll look into it for a future version, but for now, all you can do is copy the results from the individual coefficients view.
Re: Individual coefficients in Panel cointegration not saved with btwcoefs
Hello, Glenn!
Has something changed since 2017? Is it possible to save individual coefficients of pooled weighted DOLS?
Thank you!
Natalia
Has something changed since 2017? Is it possible to save individual coefficients of pooled weighted DOLS?
Thank you!
Natalia
Who is online
Users browsing this forum: Majestic-12 [Bot] and 61 guests