xuyiqing / fect

fixed effect counterfactual estimators
Other
53 stars 20 forks source link

Weights option (as in gsynth) #20

Open pbritteon opened 3 years ago

pbritteon commented 3 years ago

Hi Yiqing and team

I know you have mentioned that you are still in the process of developing this package (which is great by the way)...

I was just wondering whether you planned to add a weights option (like you have in the gsynth command) so that you can calculate the weighted average effect of a policy across treated units with unequal population sizes (e.g. when your data is aggregated at an area level)?

Many thanks, Phil

xuyiqing commented 3 years ago

That seems fairly easy to do. We'll write it down. Thank you so much, Phil!

On Wed, May 26, 2021 at 9:14 AM pbritteon @.***> wrote:

Hi Yiqing and team

I know you have mentioned that you are still in the process of developing this package (which is great by the way)...

I was just wondering whether you planned to add a weights option (like you have in the gsynth command) so that you can calculate the weighted average effect of a policy across treated units with unequal population sizes (e.g. when your data is aggregated at an area level)?

Many thanks, Phil

— You are receiving this because you are subscribed to this thread. Reply to this email directly, view it on GitHub https://github.com/xuyiqing/fect/issues/20, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2PKGA2SUSGZTX442TMKODTPUM75ANCNFSM45SM3QSQ .

pbritteon commented 2 years ago

Hi Yiqing

Just wondering whether you have had chance to add this feature since my last message? I am using gsynth in a project that requires weightings but would like to use fect to take advantage of its different features.

Many thanks, Phil

xuyiqing commented 2 years ago

Thank you for the nudge! Ziyi, maybe we can incorporate this in this round of revision?

On Tue, Jun 28, 2022 at 7:04 AM pbritteon @.***> wrote:

Hi Yiqing

Just wondering whether you have had chance to add this feature since my last message? I am using gsynth in a project that requires weightings but would like to use fect to take advantage of its different features.

Many thanks, Phil

— Reply to this email directly, view it on GitHub https://github.com/xuyiqing/fect/issues/20#issuecomment-1168770760, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2PKGEBURKP4RZJSKFQDWLVRMA63ANCNFSM45SM3QSQ . You are receiving this because you commented.Message ID: @.***>

-- Yiqing Xu

Assistant Professor Department of Political Science Stanford University https://yiqingxu.org/

bnglasner commented 2 years ago

Just tagging on that it would be very helpful!

xuyiqing commented 2 years ago

Thank you. We're updating it now.

On Tue, Aug 9, 2022 at 8:54 AM bnglasner @.***> wrote:

Just tagging on that it would be very helpful!

— Reply to this email directly, view it on GitHub https://github.com/xuyiqing/fect/issues/20#issuecomment-1209569709, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2PKGAT6IB7SUWGVKSPQJDVYJ5K7ANCNFSM45SM3QSQ . You are receiving this because you commented.Message ID: @.***>

-- Yiqing Xu

Assistant Professor Department of Political Science Stanford University https://yiqingxu.org/

jyl19 commented 1 year ago

Hi Yiqing,

Just wanted to tag along and say that adding in weights would be super helpful!

xuyiqing commented 1 year ago

Thanks for the nudge!

Hi Ziyi,

Will you have time to add it recently?

Best, Yiqing

On Tue, Nov 22, 2022 at 6:54 PM jyl19 @.***> wrote:

Hi Yiqing,

Just wanted to tag along and say that adding in weights would be super helpful!

— Reply to this email directly, view it on GitHub https://github.com/xuyiqing/fect/issues/20#issuecomment-1324482896, or unsubscribe https://github.com/notifications/unsubscribe-auth/AB2PKGA7HWB7TFU6JBI4HJDWJWBNHANCNFSM45SM3QSQ . You are receiving this because you commented.Message ID: @.***>

-- Yiqing Xu

Assistant Professor Department of Political Science Stanford University https://yiqingxu.org/

bnglasner commented 1 year ago

Hi,

I wanted to see if this had any updates. I am not seeing it in the most recent version.

Thanks!

lzy318 commented 1 year ago

Sorry for the delay. Fect now incorporates the option "W" and you can specify the weight variable using that option. In visualization, you can use the command plot(out, weight = TRUE) to visualize the weighted dynamic treatment effects.