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

From |
Isabelle.Roux@ehess.fr |

To |
statalist@hsphsun2.harvard.edu |

Subject |
Re: AW: st: AW: AW: conditional logit problem |

Date |
Fri, 27 Mar 2009 14:09:22 +0100 (CET) |

Dear Annalisa, Sorry for adding trivial points. I'm not econometrician and discovered the difference few time ago...However I think that you raised an important Stata question. If I find intersting commands, I will send it to the Statalist Best Dear Isabelle, > > many thanks for your e-mail. > Maybe I didn't express myself very well. I know the difference between the > nested logit and the conditional logit. > I was just wondering if there is a "technical" difference in terms of > stata > commands and outputs since we get the same problem. > I am relatively new in estimating in Stata, so probably I don't know the > possible solutions in terms of commands, but I know the theoretical > differences across the methods. > > Best, > > Annalisa > > > --On 27 March 2009 12:35 +0100 Isabelle.Roux@ehess.fr wrote: > >> Dear Martin and Annalisa, >> >> For me the difference between the conditional mixed model, which is >> mine, >> and the nested model, is that the second is "sequential", and the not >> the >> first. >> For example, the typic issue solved thanks to the conditional logit is >> "explain the transport choices of individuals: take the bus, or the car, >> or walk". The nested logit explains sequential choices. For example, >> first >> choose between the car and the bus, the between the blue car and the red >> car (or for an economic example: first the firm decide to export or to >> do >> a FDI, second the country of the FDI.) >> >> Martin, indeed I have the Stata10 version, but only the Stata8 manual ! >> So >> I will try the "xtmelogit" command, thank you. >> If Annalisa is economist, (and even if she is not), a very good example >> of >> nested logit can be found here: >> http://www.cepii.fr/anglaisgraph/workpap/summaries/2007/wp07-07.htm >> >>> Dear Martin, >>> >>> my problem is that I should estimate a nested (mixed) multinomial logit >>> model. It seems the xtmelogit command does not allow to run multinomial >>> logit models. >>> I am estimating a RUM so stata 10 seems more appropriate to my model >>> than >>> stata 8, but I cannot sort out the problem and I also received messages >>> like the one's Isabelle received. I also tried to interact the >>> variables >>> like Isabelle is suggesting, but it didn't work. >>> >>> Maybe Isabelle's problem is different from mine. >>> I have been spending several time on the commands, but I didn't find a >>> solution to get a correct estimate, maybe because I am new to the >>> nested >>> logit. >>> I checked on the Stata manual, Stata help the Cameron and Trivedi's >>> book >>> "Microecnometrics using stata", their website and several other >>> documents, but I could not find a command. >>> Maybe this is just a problem linked to a nested logit. That's why I am >>> planning to estimate it by programming myself the ML. >>> >>> I replied to Isabelle's message because it seems that the problems are >>> strictly correlated, but I talked on the base of my experience. >>> >>> If you have any suggestions are more than welcome! >>> >>> Best, >>> >>> Annalisa >>> >>> >>> >>> --On 27 March 2009 11:39 +0100 Martin Weiss <martin.weiss1@gmx.de> >>> wrote: >>> >>>> >>>> <> >>>> >>>> Annalisa, >>>> >>>> what is the difference between your proposal and -xtmelogit-? One >>>> difference for Isabelle obviously would be that Stata 8 does not >>>> provide >>>> her with this commmand, as it was, AFAIK, introduced in Stata 10. But >>>> she >>>> might have access to a more recent Stata version... >>>> >>>> >>>> >>>> HTH >>>> Martin >>>> >>>> >>>> -----Ursprüngliche Nachricht----- >>>> Von: owner-statalist@hsphsun2.harvard.edu >>>> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Annalisa >>>> Marini Gesendet: Freitag, 27. März 2009 11:35 >>>> An: statalist@hsphsun2.harvard.edu >>>> Betreff: Re: st: AW: AW: conditional logit problem >>>> >>>> Dear Isabelle, >>>> >>>> If I am not wrong you have a mixed logit. I am also working on a mixed >>>> logit by using stata and I think one solution (I am also starting to >>>> use) >>>> is that of programming yourself the ML rather than using stata >>>> commands. >>>> >>>> If anyone has other (better and wuicker) suggestions are more than >>>> welcome since I have been spending a lot of time on these nested >>>> logit >>>> commands! >>>> >>>> Many thanks. >>>> >>>> Annalisa >>>> >>>> >>>> --On 27 March 2009 11:28 +0100 Isabelle.Roux@ehess.fr wrote: >>>> >>>>> Thank you very much Martin, for your very useful help. >>>>> >>>>> -First of all I just had a look at "va" and you were right: there is >>>>> a >>>>> pb >>>>> with it because sometimes I have different va for a same firm. So I >>>>> have >>>>> to check how I obtained it and to improve that. >>>>> >>>>> -Secondly I sought in the STATA8 manual, which explains that >>>>> individual >>>>> variables (like va, or sex if the observations were human), have to >>>>> be >>>>> multiplied by dummy variables for the choices: >>>>> >>>>> it is the beginning of the example's dataset in the manual: >>>>> id car choice dealer sex income >>>>> 1 American 0 18 male 46 >>>>> 1 Japan 0 8 male 46 >>>>> 1 Europe 1 5 male 46 >>>>> >>>>> 2 American 0 17 male 26 >>>>> 2 Japan 1 6 male 26 >>>>> 2 Europe 0 2 male 26 >>>>> >>>>> "car": nationality of the car's manufacturer >>>>> "dealer": number of dealerships of each nationality in the consumer's >>>>> city >>>>> >>>>> *** >>>>> gen japan=(car==2) >>>>> gen europe=(car==3) >>>>> gen sexeur=sex*japan >>>>> gen sexjap=sex*jap >>>>> gen incjap=income*japan >>>>> gen inceur=income*europe >>>>> *** >>>>> >>>>> and to run : >>>>> >>>>> *** >>>>> clogit choice japan europe sexjap sexeur incjap inceur delaer, >>>>> grou(id) >>>>> *** >>>>> >>>>> >>>>> But I am a bit afraid of doing that, because in all I have 66 >>>>> countries, >>>>> and 7 firm's variables, so, even if I keep only 2 or 3 firm's >>>>> variables, >>>>> there will be a lot of dummies in my results. >>>>> >>>>> >>>>> >>>>> >>>>>> >>>>>> <> >>>>>> >>>>>> One thing for Isabelle to consider: When I replace just one value of >>>>>> va >>>>>> with >>>>>> "0" during the -input-, the message does not appear for "va", but >>>>>> for >>>>>> "ln(va)". So Isabelle might want to check her data set and maybe >>>>>> report >>>>>> -inspect va- to the list... >>>>>> >>>>>> >>>>>> >>>>>> HTH >>>>>> Martin >>>>>> >>>>>> >>>>>> -----Ursprüngliche Nachricht----- >>>>>> Von: owner-statalist@hsphsun2.harvard.edu >>>>>> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von Martin >>>>>> Weiss Gesendet: Freitag, 27. März 2009 10:10 >>>>>> An: statalist@hsphsun2.harvard.edu >>>>>> Betreff: st: AW: conditional logit problem >>>>>> >>>>>> >>>>>> <> >>>>>> >>>>>> Actually, Stata complains whether you enter "va" or its log into >>>>>> -clogit-: " >>>>>> note: ... omitted because of no within-group variance." It would be >>>>>> weird for the log transform to change the effect of va as the >>>>>> transform >>>>>> itself cannot generate any variance within the groups. >>>>>> >>>>>> The problem is mentioned in [R]clogit, p. 284. >>>>>> >>>>>> ************* >>>>>> clear* >>>>>> inp double siren va str10 country tax double GDP choice >>>>>> 17251067 94997 Spain .35 777000000000 1 >>>>>> 17251067 94997 Brazil .34 486000000000 0 >>>>>> 17251067 94997 Italy .38 1330000000000 0 >>>>>> 17251068 28142 Brazil .34 486000000000 1 >>>>>> 17251068 28142 Spain .35 777000000000 0 >>>>>> 17251068 28142 Italy .38 133000000000 0 >>>>>> 17251069 75758 Italy .38 13300000000 1 >>>>>> 17251069 75758 Spain .35 777000000000 0 >>>>>> 17251069 75758 Brazil .34 486000000000 0 >>>>>> end >>>>>> l, noo sepby(va) >>>>>> g lntax=log(tax) >>>>>> g lnGDP=log(GDP) >>>>>> encode country, gen(newcountry) >>>>>> drop country >>>>>> rename newcountry country >>>>>> * w/o va >>>>>> clogit choice country lntax lnGDP , group(siren) iter(10) nolog >>>>>> *with va >>>>>> clogit choice country lntax lnGDP va, group(siren) iter(10) nolog >>>>>> g lnva=log(va) >>>>>> *with ln(va) >>>>>> clogit choice country lntax lnGDP lnva, group(siren) iter(10) nolog >>>>>> ************* >>>>>> >>>>>> Might -asclogit- be a way out for Isabelle? >>>>>> >>>>>> HTH >>>>>> Martin >>>>>> >>>>>> >>>>>> -----Ursprüngliche Nachricht----- >>>>>> Von: owner-statalist@hsphsun2.harvard.edu >>>>>> [mailto:owner-statalist@hsphsun2.harvard.edu] Im Auftrag von >>>>>> Isabelle.Roux@ehess.fr >>>>>> Gesendet: Freitag, 27. März 2009 09:42 >>>>>> An: statalist@hsphsun2.harvard.edu >>>>>> Betreff: st: conditional logit problem >>>>>> >>>>>> Dear statalisters, >>>>>> >>>>>> I have a dataset with firms, to which is attributed a number called >>>>>> "siren", and characteristics of thses firms (exportations, size, >>>>>> value >>>>>> added...). I have too the country in which they decide to invest, >>>>>> and >>>>>> characteristics of this country (GDP, population, tax rate, labor >>>>>> costs...) >>>>>> >>>>>> So my database looks like this (it is an example with 3 firms which >>>>>> choose one unique country): >>>>>> siren va country tax GDP choice >>>>>> 17251067 94997 Spain .35 7.77e+11 >>>>>> 1 >>>>>> 17251067 94997 Brazil .34 4.86e+11 >>>>>> 0 >>>>>> 17251067 94997 Italy .38 1.33e+12 0 >>>>>> >>>>>> 3.025e+08 28142 Brazil .34 4.86e+11 1 >>>>>> 3.025e+08 28142 Spain .35 7.77e+11 0 >>>>>> 3.025e+08 28142 Italy .38 1.33e+12 0 >>>>>> >>>>>> 3.026e+08 75758 Italy .38 1.33e+12 1 >>>>>> 3.026e+08 75758 Spain .35 7.77e+11 0 >>>>>> 3.026e+08 75758 Brazil .34 4.86e+11 >>>>>> 0 >>>>>> >>>>>> >>>>>> When I run a conditional logit with only countries'characteristics >>>>>> as >>>>>> regressors (***clogit choice country lntax lnGDP, group(siren)**, >>>>>> where >>>>>> lntax and lnGDP are the log of tax and GDP), it is OK. >>>>>> But what I don't understand is this point: >>>>>> >>>>>> -When I add value added as a control variable (***clogit choice >>>>>> country >>>>>> lntax lnGDP va, group(siren)***), it works, even if the coefficient >>>>>> for >>>>>> va is strange. >>>>>> -When I add the log of value added as a control variable ((***clogit >>>>>> choice country lntax lnGDP lnva, group(siren)***), STATA refuses to >>>>>> provide results and write:"outcome does not varies in any group". >>>>>> >>>>>> So I wonder why it is ok in a case and not in the other else which >>>>>> is >>>>>> very similar, and I don't know what kind of logit to run which >>>>>> allows >>>>>> me >>>>>> to mix the two types of variables. >>>>>> >>>>>> >>>>>> >>>>>> Thank you very much for help, >>>>>> >>>>>> Isabelle >>>>>> >>>>>> >>>>>> * >>>>>> * 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/ >>>> >>>> >>>> >>>> ---------------------- >>>> Annalisa Marini >>>> Department of Economics >>>> University of Bristol >>>> 8 Woodland Road >>>> Bristol BS8 1TN >>>> United Kingdom >>>> >>>> e-mail: annalisa.marini@bristol.ac.uk >>>> >>>> * >>>> * 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/ >>> >>> >>> >>> ---------------------- >>> Annalisa Marini >>> Department of Economics >>> University of Bristol >>> 8 Woodland Road >>> Bristol BS8 1TN >>> United Kingdom >>> >>> e-mail: annalisa.marini@bristol.ac.uk >>> >>> * >>> * 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/ > > > > ---------------------- > Annalisa Marini > Department of Economics > University of Bristol > 8 Woodland Road > Bristol BS8 1TN > United Kingdom > > e-mail: annalisa.marini@bristol.ac.uk > > * > * 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/

**References**:**st: Build groups with the same first two numbers of SIC***From:*"Hua Pan" <panhua@gmx.de>

**st: RE: Build groups with the same first two numbers of SIC***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

**Re: st: RE: Build groups with the same first two numbers of SIC***From:*"Michael I. Lichter" <mlichter@buffalo.edu>

**RE: st: RE: Build groups with the same first two numbers of SIC***From:*"Nick Cox" <n.j.cox@durham.ac.uk>

**st: conditional logit problem***From:*Isabelle.Roux@ehess.fr

**st: AW: conditional logit problem***From:*"Martin Weiss" <martin.weiss1@gmx.de>

**st: AW: AW: conditional logit problem***From:*"Martin Weiss" <martin.weiss1@gmx.de>

**Re: st: AW: AW: conditional logit problem***From:*Isabelle.Roux@ehess.fr

**Re: st: AW: AW: conditional logit problem***From:*Annalisa Marini <annalisa.marini@bristol.ac.uk>

**AW: st: AW: AW: conditional logit problem***From:*"Martin Weiss" <martin.weiss1@gmx.de>

**Re: AW: st: AW: AW: conditional logit problem***From:*Annalisa Marini <annalisa.marini@bristol.ac.uk>

**Re: AW: st: AW: AW: conditional logit problem***From:*Isabelle.Roux@ehess.fr

**Re: AW: st: AW: AW: conditional logit problem***From:*Annalisa Marini <annalisa.marini@bristol.ac.uk>

- Prev by Date:
**st: Relation between bootstrap sample size and number of replications** - Next by Date:
**RE: AW: st: Calculate the average bid-ask spread for each centile** - Previous by thread:
**Re: AW: st: AW: AW: conditional logit problem** - Next by thread:
**Re: st: Build groups with the same first two numbers of SIC** - Index(es):

© Copyright 1996–2015 StataCorp LP | Terms of use | Privacy | Contact us | What's new | Site index |