Dear all, I want to estimate a model in which individuals self-select into two different actions (e.g. invest or not invest). Moreover, the factors that influence the selection decision also affect the ultimate outcome variable (e.g. return on investment). That is, I want to estimate a model with endogenous selection. My question is: Which R package supports this kind of estimation? To me it seems like the package sampleSelection (https://cran.r-project.org/web/packages/sampleSelection/sampleSelection.pdf ) can only be used in case of a SAMPLE selection, i.e. in the example above: only individuals that invest are observed. Yet in my case, both actions are observed but the decision which action to choose is endogenous. Or does this package also support self-selection models? Thank you very much in advance. Best, Johannes
Dear Johannes
You can use function selection() of the sampleSelection package and
estimate an endogenous switching regression ("tobit-5") model, where
you have the selection equation to model investmentment vs.
non-investment and you have two outcome equations, one for firms that
invest and the other for firms that do not invest.
Best regards,
Arne
On 18 September 2015 at 07:43, Johannes Muck <Muck at
econ.uni-frankfurt.de> wrote:> Dear all,
>
> I want to estimate a model in which individuals self-select into two
> different actions (e.g. invest or not invest). Moreover, the factors that
> influence the selection decision also affect the ultimate outcome variable
> (e.g. return on investment). That is, I want to estimate a model with
> endogenous selection.
>
> My question is: Which R package supports this kind of estimation?
> To me it seems like the package sampleSelection
>
(https://cran.r-project.org/web/packages/sampleSelection/sampleSelection.pdf
> ) can only be used in case of a SAMPLE selection, i.e. in the example
above:
> only individuals that invest are observed. Yet in my case, both actions are
> observed but the decision which action to choose is endogenous. Or does
this
> package also support self-selection models?
>
> Thank you very much in advance.
>
> Best,
>
> Johannes
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
--
Arne Henningsen
http://www.arne-henningsen.name
Dear Arne,
thank you very much!
Best,
Johannes
-----Urspr?ngliche Nachricht-----
Von: Arne Henningsen [mailto:arne.henningsen at gmail.com]
Gesendet: Samstag, 19. September 2015 07:07
An: Johannes Muck <Muck at econ.uni-frankfurt.de>
Cc: r-help at r-project.org
Betreff: Re: [R] Estimating Endogenous Selection Model
Dear Johannes
You can use function selection() of the sampleSelection package and estimate an
endogenous switching regression ("tobit-5") model, where you have the
selection equation to model investmentment vs.
non-investment and you have two outcome equations, one for firms that invest and
the other for firms that do not invest.
Best regards,
Arne
On 18 September 2015 at 07:43, Johannes Muck <Muck at
econ.uni-frankfurt.de> wrote:> Dear all,
>
> I want to estimate a model in which individuals self-select into two
> different actions (e.g. invest or not invest). Moreover, the factors
> that influence the selection decision also affect the ultimate outcome
> variable (e.g. return on investment). That is, I want to estimate a
> model with endogenous selection.
>
> My question is: Which R package supports this kind of estimation?
> To me it seems like the package sampleSelection
> (https://cran.r-project.org/web/packages/sampleSelection/sampleSelecti
> on.pdf
> ) can only be used in case of a SAMPLE selection, i.e. in the example
above:
> only individuals that invest are observed. Yet in my case, both
> actions are observed but the decision which action to choose is
> endogenous. Or does this package also support self-selection models?
>
> Thank you very much in advance.
>
> Best,
>
> Johannes
>
> ______________________________________________
> R-help at r-project.org mailing list -- To UNSUBSCRIBE and more, see
> https://stat.ethz.ch/mailman/listinfo/r-help
> PLEASE do read the posting guide
> http://www.R-project.org/posting-guide.html
> and provide commented, minimal, self-contained, reproducible code.
--
Arne Henningsen
http://www.arne-henningsen.name