Bookmark and Share

Notice: On March 31, it was announced that Statalist is moving from an email list to a forum. The old list will shut down on April 23, and its replacement, statalist.org is already up and running.


[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

AW: st: why Margins gives "not estimable" ?


From   Reinhardt Jan Dietrich <jan.reinhardt@paranet.ch>
To   "statalist@hsphsun2.harvard.edu" <statalist@hsphsun2.harvard.edu>
Subject   AW: st: why Margins gives "not estimable" ?
Date   Sun, 12 Feb 2012 12:43:46 +0000

Franscesco -

Did you try the following:

margins, dydx(DUM) subpop (CAT CAT2)

Otherwise margins may have problems with the cluster vce ... Try vce (robust) and see if it works.
Best
Jan




________________________________________
Von: owner-statalist@hsphsun2.harvard.edu [owner-statalist@hsphsun2.harvard.edu]&quot; im Auftrag von &quot;Francesco [cariboupad@gmx.fr]
Gesendet: Samstag, 11. Februar 2012 18:58
An: statalist@hsphsun2.harvard.edu
Betreff: Re: st: why Margins gives "not estimable" ?

Many thanks Cameron,

However the model specification is exactly as given in my first mail,
there are no hidden terms or complicated interactions...
And on top of that my sample size is very, very large...

Any other ideas?
Have a nice day

Best

On 11 February 2012 16:23, Cameron McIntosh <cnm100@hotmail.com> wrote:
> I don't know about your code, but perhaps this is due to numerical instabilities stemming from a complex model (many interactions terms) and possibly insufficient sample size? You may want to check the archives for threads tied to "margins not estimable" for example, and perhaps see:
> Williams, R. Margins Part 2: Marginal Effects.http://www.nd.edu/~rwilliam/stats3/Margins02.pdf
>
> Cornelissen, T., & Sonderhof, K. (2009). Marginal effects in the probit model with a triple dummy variable interaction term. (Diskussionspapiere der Wirtschaftswissenschaftlichen Fakultät der Universität Hannover DP-386). Hannover, Germany: School of Economics and Management, Hannover Leibniz University.http://www.wiwi.uni-hannover.de/Forschung/Diskussionspapiere/dp-386.pdf
>
> Anderson, S., & Newell, R.G. (2003). Simplified marginal effects in discrete choice models. Economics Letters, 81, 321–326.https://www.msu.edu/~sta/AndersonNewell_mfx_EconLetters.pdf
>
> Carlevaro, F., & Sénégas, M.-A. (2006). Simplified marginal effects in discrete choice models: A correction. Economics Letters, 92(1), 44-46.
>
> Mullahy, J. (November 2011). Marginal Effects in Multivariate Probit and Kindred Discrete and Count Outcome Models, with Applications in Health Economics. NBER Working Paper No. 17588. http://works.bepress.com/cgi/viewcontent.cgi?article=1001&context=johnmullahy
>
> Bartus, T. (2005). Estimation of marginal effects using margeff. The Stata Journal, 5(3), 309–329.http://www.stata-journal.com/sjpdf.html?articlenum=st0086http://econpapers.repec.org/software/bocbocode/s445001.htm
>
> Frondel, M., & Vance, C. (September 2009). On Marginal and Interaction Effects: The Case of Heckit and Two-Part Models. Ruhr Economic Papers #138. Bibliogra? sche Informationen der Deutschen Nationalbibliothek.http://repec.rwi-essen.de/files/REP_09_138.pdf
>
> Chen, X., & Wilson, B. (2011). Visualizing Marginal Effects from Interactions in Generalized Linear Models. SAS Global Forum 2011, Statistics and Data Analysis, Paper 350-2011.http://support.sas.com/resources/papers/proceedings11/350-2011.pdf
>
> Basu, A., & Rathouz, P.J. (2005). Estimating marginal and incremental effects on health outcomes using flexible link and variance function models. Biostatistics, 6(1), 93–109.http://biostatistics.oxfordjournals.org/content/6/1/93.full.pdf
>
>
> Cam
>
> ----------------------------------------
>> From: cariboupad@gmx.fr
>> Date: Sat, 11 Feb 2012 16:06:49 +0100
>> Subject: st: why Margins gives "not estimable" ?
>> To: statalist@hsphsun2.harvard.edu
>>
>> Dear Statalist,
>>
>> I have a simple, yet puzzling question (at least for me) about -margins.
>>
>> I run a fixed effect regression and I would like to understand the
>> effect of a dummy variable (DUM) interacted with a categorical
>> variable (CAT)
>> CAT can take 5 values (1, 2, 3, 4 and 5) lets say.
>>
>> When I run
>>
>> -xtreg Y 1b.CAT##DUM, vce(cluster id)
>>
>> I get the results
>> and if I type
>>
>> -margins CAT, dydx(DUM)
>> I get by how much I increase the predicted values of the output Y when
>> DUM=1 and according to the values of CAT.
>> So far, so good.
>>
>> However, if in the original regression I include another categorical
>> variable : CAT2 (7 possible values)
>>
>> -xtreg Y 1b.CAT##DUM i.CAT2, vce(cluster id)
>>
>> then
>> -margins CAT, dydx(DUM)
>> or
>> -margins CAT, dydx(DUM) at(CAT2="a particular value of CAT2)
>> or even -margins CAT, dydx(DUM) over(CAT2)
>>
>> they all return "not estimable"...
>>
>> Do you have an idea ? I am probably missing some important option or
>> syntax in the margins command ?
>>
>> Many thanks
>> *
>> * For searches and help try:
>> * http://www.stata.com/help.cgi?search
>> * http://www.stata.com/support/statalist/faq
>> * http://www.ats.ucla.edu/stat/stata/
>
> *
> *   For searches and help try:
> *   http://www.stata.com/help.cgi?search
> *   http://www.stata.com/support/statalist/faq
> *   http://www.ats.ucla.edu/stat/stata/

*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/
*
*   For searches and help try:
*   http://www.stata.com/help.cgi?search
*   http://www.stata.com/support/statalist/faq
*   http://www.ats.ucla.edu/stat/stata/


© Copyright 1996–2014 StataCorp LP   |   Terms of use   |   Privacy   |   Contact us   |   Site index