From wgreene at stern.nyu.edu Fri Dec 1 14:42:20 2017 From: wgreene at stern.nyu.edu (William Greene) Date: Thu, 30 Nov 2017 22:42:20 -0500 Subject: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit In-Reply-To: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> References: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> Message-ID: Federica. Try adding ;ALL to the command, to request the full set of statistics for the elasticity. /Bill Greene On Mon, Nov 27, 2017 at 6:21 AM, Liberini Federica wrote: > Hello, > > I have estimated a random parameter conditional logit model, using the > command NLOGIT. > So far, I used the option ";Effects: x (*)" to obtain the elasticities of > choosing each model's alternative w.r.t to variable x. Is there a way of > obtaining standard errors for these elasticities? > I tried using the command "Partial Effects", but Limpdep returns the error > message saying that "Previous model did not store model setup for > PARTIALS.". > > Many Thanks, > Federica > > p.s.> here's a synthesis of the command I am using now > > nlogit; lhs=choice,nij,altcode > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US > ; model: U(AT,BE,BR,CA,CH,DE,DK,DOM,ES, > FI,FR,GB,IE,IT,NL,NO,RU,SE,US)= > FRb0,GBb0,IEb0,ITb0,NLb0,NOb0,RUb0,SEb0,0> + > FIoloc,FRoloc,GBoloc,IEoloc,IToloc,NLoloc,NOoloc,RUoloc,SEoloc,0> * X1 + > > cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx>* X2 + > mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx>*Dumm1*X2 + > > <0,0,0,0,0,0,0,domtx,0,0,0,0,0,0,0,0,0,0,0>*X2 + > <0,0,0,0,0,0,0,mndomtx,0,0,0,0,0,0,0,0,0,0,0>*Dumm1*X2 + > > ; fcn= cbtx(n) > ; rpl > ; maxit=400 > ; halton; pts=50 > ; alg=bfgs > ; effects: X2 (*) $ > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/0RmgBrswbbX4s7?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From Lixian.Qian at xjtlu.edu.cn Fri Dec 1 18:11:12 2017 From: Lixian.Qian at xjtlu.edu.cn (Lixian Qian) Date: Fri, 1 Dec 2017 07:11:12 +0000 Subject: [Limdep Nlogit List] Line search does not improve the function. Message-ID: Dear professors, I am running a Nested Logit Model in NLogit v5.0. I find the location of alternative specific constants (ASCs) in the utility function can impact the model convergence. When I specify the utility function with 3 alternatives as: U(A) = a1*X1 + a2*X2 / U(B) = a1*X1 + a2*X2 + asc_b + age_b*Age + sex_b *Gender / U(C) = a1*X1 + a2*X2 + asc_c + age_c*Age + sex_c *Gender The model estimation shows that Line search at iteration 61 does not improve fn. Exiting optimization. However, when I make a minor change on the utility functions to U(A) = a1*X1 + a2*X2 / U(B) = asc_b+ a1*X1 + a2*X2 + age_b*Age + sex_b *Gender / U(C) = asc_c + a1*X1 + a2*X2 + age_c*Age + sex_c *Gender The model can successfully converge, with the exact same LL function, all estimated coefficients as well as standard errors as in the previous case (though not converged as mentioned in output). I don't know what is wrong with the first case. Thank you and appreciate your advices. Best, Lixian From wgreene at stern.nyu.edu Fri Dec 1 23:40:45 2017 From: wgreene at stern.nyu.edu (William Greene) Date: Fri, 1 Dec 2017 07:40:45 -0500 Subject: [Limdep Nlogit List] Line search does not improve the function. In-Reply-To: References: Message-ID: Lixian. There is nothing wrong with either estimation. The difference is small rounding error. The message indicates that the log likelihood is relatively flat near the maximizer. The two specifications are logically equivalent, but in computing the logL, very small rounding error depends on the actual order in which the computations are done. /Bill Greene On Fri, Dec 1, 2017 at 2:11 AM, Lixian Qian wrote: > Dear professors, > > I am running a Nested Logit Model in NLogit v5.0. > > I find the location of alternative specific constants (ASCs) in the > utility function can impact the model convergence. > > When I specify the utility function with 3 alternatives as: > U(A) = a1*X1 + a2*X2 / > U(B) = a1*X1 + a2*X2 + asc_b + age_b*Age + sex_b *Gender / > U(C) = a1*X1 + a2*X2 + asc_c + age_c*Age + sex_c *Gender > The model estimation shows that Line search at iteration 61 does not > improve fn. Exiting optimization. > > However, when I make a minor change on the utility functions to > U(A) = a1*X1 + a2*X2 / > U(B) = asc_b+ a1*X1 + a2*X2 + age_b*Age + sex_b *Gender / > U(C) = asc_c + a1*X1 + a2*X2 + age_c*Age + sex_c *Gender > The model can successfully converge, with the exact same LL function, all > estimated coefficients as well as standard errors as in the previous case > (though not converged as mentioned in output). > > I don't know what is wrong with the first case. > > Thank you and appreciate your advices. > > > Best, > Lixian > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/Rv1VB2fOnb0vf4?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From wgreene at stern.nyu.edu Mon Dec 4 11:22:34 2017 From: wgreene at stern.nyu.edu (William Greene) Date: Sun, 3 Dec 2017 19:22:34 -0500 Subject: [Limdep Nlogit List] wtp in lclogit In-Reply-To: <72D6B3FEC474FA40B4981EDD2D672981CD423125@CNMB02WVP.core-res.rootcore.local> References: <72D6B3FEC474FA40B4981EDD2D672981CD423125@CNMB02WVP.core-res.rootcore.local> Message-ID: Charles. The matrix for WTP is created before the program has detected what type of model will be computed. The latent class logit model is a MNL model in each class. Therefore, the WTP in each class is the same for every individual - it is just the same ratio of parameters for everyone. Since it is not known which class any individual is in, it is not possible to discern which of those (two in your case) ratio applies to a given person. For that reason, the matrix wtp_i is not filled. It would just be the same value for each individual. Regards, Bill Greene On Fri, Nov 24, 2017 at 12:49 PM, RAUX Charles < Charles.Raux at laet.ish-lyon.cnrs.fr> wrote: > Hello, > I have a specification of latent class multinomial model (below) > > lclogit; choices=air, car, bus, train, none > ; lhs=choicem > ; model: U(air, car, bus, train) = > + * duration + pc * price > / U(none) = anone > ; show model > ; pds=6; pts=2 > ; wtp=da/pc, dc/pc, db/pc, dt/pc$ > > This works fine, parameters are significant and the matrix wtpi is created > with four columns and nearly 300 rows (the individuals). But filled only > with zero. What is wrong? > Charles Raux > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/e4MrBZUOQbk7cJ?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From liberini at kof.ethz.ch Mon Dec 4 20:25:25 2017 From: liberini at kof.ethz.ch (Liberini Federica) Date: Mon, 4 Dec 2017 09:25:25 +0000 Subject: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit In-Reply-To: References: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> Message-ID: <213F594826F3B9428143CEB7C51517E04C753413@MBX23.d.ethz.ch> Thank you very much for your reply. I have tried the "; ALL $" option at the end of the command, but the output did not change for the version I got without the "; ALL $" option. To be more precise, this is (a part of) the matrix of elasticities that I get from the command shown earlier (augmented by the "; ALL $" option). Any other way of getting the Standard Errors of these elasticities? Many thanks Federica Elasticity wrt change of X in row choice on Prob[column choice] --------+----------------------------------------------------------------------- ALTSTR | AT BE BR CA CH DE DK DOM --------+----------------------------------------------------------------------- AT| -.4368 -.0122 -.0151 .0156 .0140 .0220 .0076 .0043 BE| -.0454 2.3870 -.2807 .0040 .0154 .0243 -.0458 .0045 BR| -.0504 -.1873 2.9656 -.0132 .0030 .0021 -.0501 .0015 CA| .0320 -.0083 -.0130 -1.3293 .0569 .0628 .0320 .0209 CH| .0096 .0027 .0018 .0154 -1.7195 .0182 .0095 .0146 DE| .0628 .0166 .0077 .0921 .0996 -1.4425 .0623 .0430 DK| .0135 -.0291 -.0354 .0310 .0286 .0380 -.3857 .0088 DOM| -.0036 -.0018 -.0014 -.0055 -.0089 -.0070 -.0036 .0006 --------+----------------------------------------------------------------------- ALTSTR | ES FI FR GB IE IT NL NO --------+----------------------------------------------------------------------- AT| -.0038 .0057 -.0122 .0016 .0166 .0020 .0076 .0016 BE| -.1400 -.0604 -.1697 -.0902 .0167 -.0880 -.0055 -.0943 BR| -.1141 -.0602 -.1843 -.0866 .0005 -.0808 -.0486 -.0840 CA| .0067 .0272 -.0076 .0209 .0634 .0191 .0303 .0175 CH| .0047 .0084 .0049 .0069 .0209 .0067 .0092 .0067 DE| .0302 .0549 .0219 .0468 .1068 .0442 .0631 .0449 DK| -.0106 .0104 -.0266 .0051 .0339 .0010 .0147 .0053 DOM| -.0025 -.0034 -.0022 -.0039 -.0076 -.0028 -.0039 -.0030 --------+-------------------------- ALTSTR | RU SE US --------+-------------------------- AT... -----Original Message----- From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of William Greene Sent: 01 December 2017 04:42 To: Limdep and Nlogit Mailing List Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit Federica. Try adding ;ALL to the command, to request the full set of statistics for the elasticity. /Bill Greene On Mon, Nov 27, 2017 at 6:21 AM, Liberini Federica > wrote: > Hello, > > I have estimated a random parameter conditional logit model, using the > command NLOGIT. > So far, I used the option ";Effects: x (*)" to obtain the elasticities > of choosing each model's alternative w.r.t to variable x. Is there a > way of obtaining standard errors for these elasticities? > I tried using the command "Partial Effects", but Limpdep returns the > error message saying that "Previous model did not store model setup > for PARTIALS.". > > Many Thanks, > Federica > > p.s.> here's a synthesis of the command I am using now > > nlogit; lhs=choice,nij,altcode > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US > ; model: U(AT,BE,BR,CA,CH,DE,DK,DOM,ES, > FI,FR,GB,IE,IT,NL,NO,RU,SE,US)= > FRb0,GBb0,IEb0,ITb0,NLb0,NOb0,RUb0,SEb0,0> + > FIoloc,FRoloc,GBoloc,IEoloc,IToloc,NLoloc,NOoloc,RUoloc,SEoloc,0> * X1 > + > > cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx>* X2 + > mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx>*Dumm1*X2 > + > > <0,0,0,0,0,0,0,domtx,0,0,0,0,0,0,0,0,0,0,0>*X2 + > <0,0,0,0,0,0,0,mndomtx,0,0,0,0,0,0,0,0,0,0,0>*Dumm1*X2 + > > ; fcn= cbtx(n) > ; rpl > ; maxit=400 > ; halton; pts=50 > ; alg=bfgs > ; effects: X2 (*) $ > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/EM1LB5UoXXWLUR?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au From liberini at kof.ethz.ch Mon Dec 4 22:04:09 2017 From: liberini at kof.ethz.ch (Liberini Federica) Date: Mon, 4 Dec 2017 11:04:09 +0000 Subject: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit In-Reply-To: <213F594826F3B9428143CEB7C51517E04C753413@MBX23.d.ethz.ch> References: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> <213F594826F3B9428143CEB7C51517E04C753413@MBX23.d.ethz.ch> Message-ID: <213F594826F3B9428143CEB7C51517E04C75566C@MBX23.d.ethz.ch> Dear Bill, to check whether the issue was the syntax used for my estimation command, I also estimated a simpler model specification, using this alternative syntax: nlogit; lhs=choice,nij,altcode ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US ;rhs=one,altstr ;rh2=parstr ;fcn=altstr(n) ;checkdata ;pds=3 ;maxit=400 ;alg=bfgs ;pts=100; halton ;effects:altstr(*) ; ALL $ Once again, the elasticities are only displayed in the format of a matrix, with no reported SE (see a partial pasted result below). Could the matter be the version of my software (NLOGIT5)? Many thanks, Federica Elasticity wrt change of X in row choice on Prob[column choice] --------+----------------------------------------------------------------------- ALTSTR | AT BE BR CA CH DE DK DOM --------+----------------------------------------------------------------------- AT| -.1779 .0005 .0005 .0005 .0005 .0005 .0005 .0005 BE| .0019 -.2309 .0019 .0019 .0019 .0019 .0019 .0019 BR| .0009 .0009 -.2436 .0009 .0009 .0009 .0009 .0009 CA| .0013 .0013 .0013 -.1318 .0013 .0013 .0013 .0013 CH| .0003 .0003 .0003 .0003 -.0613 .0003 .0003 .0003 DE| .0016 .0016 .0016 .0016 .0016 -.0974 .0016 .0016 DK| .0010 .0010 .0010 .0010 .0010 .0010 -.1756 .0010 DOM| .2932 .2932 .2932 .2932 .2932 .2932 .2932 -.0569 --------+----------------------------------------------------------------------- ALTSTR | ES FI FR GB IE IT NL NO --------+----------------------------------------------------------------------- AT|... -----Original Message----- From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of Liberini Federica Sent: 04 December 2017 10:25 To: Limdep and Nlogit Mailing List Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit Thank you very much for your reply. I have tried the "; ALL $" option at the end of the command, but the output did not change for the version I got without the "; ALL $" option. To be more precise, this is (a part of) the matrix of elasticities that I get from the command shown earlier (augmented by the "; ALL $" option). Any other way of getting the Standard Errors of these elasticities? Many thanks Federica Elasticity wrt change of X in row choice on Prob[column choice] --------+----------------------------------------------------------------------- ALTSTR | AT BE BR CA CH DE DK DOM --------+----------------------------------------------------------------------- AT| -.4368 -.0122 -.0151 .0156 .0140 .0220 .0076 .0043 BE| -.0454 2.3870 -.2807 .0040 .0154 .0243 -.0458 .0045 BR| -.0504 -.1873 2.9656 -.0132 .0030 .0021 -.0501 .0015 CA| .0320 -.0083 -.0130 -1.3293 .0569 .0628 .0320 .0209 CH| .0096 .0027 .0018 .0154 -1.7195 .0182 .0095 .0146 DE| .0628 .0166 .0077 .0921 .0996 -1.4425 .0623 .0430 DK| .0135 -.0291 -.0354 .0310 .0286 .0380 -.3857 .0088 DOM| -.0036 -.0018 -.0014 -.0055 -.0089 -.0070 -.0036 .0006 --------+----------------------------------------------------------------------- ALTSTR | ES FI FR GB IE IT NL NO --------+----------------------------------------------------------------------- AT| -.0038 .0057 -.0122 .0016 .0166 .0020 .0076 .0016 BE| -.1400 -.0604 -.1697 -.0902 .0167 -.0880 -.0055 -.0943 BR| -.1141 -.0602 -.1843 -.0866 .0005 -.0808 -.0486 -.0840 CA| .0067 .0272 -.0076 .0209 .0634 .0191 .0303 .0175 CH| .0047 .0084 .0049 .0069 .0209 .0067 .0092 .0067 DE| .0302 .0549 .0219 .0468 .1068 .0442 .0631 .0449 DK| -.0106 .0104 -.0266 .0051 .0339 .0010 .0147 .0053 DOM| -.0025 -.0034 -.0022 -.0039 -.0076 -.0028 -.0039 -.0030 --------+-------------------------- ALTSTR | RU SE US --------+-------------------------- AT... -----Original Message----- From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of William Greene Sent: 01 December 2017 04:42 To: Limdep and Nlogit Mailing List Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit Federica. Try adding ;ALL to the command, to request the full set of statistics for the elasticity. /Bill Greene On Mon, Nov 27, 2017 at 6:21 AM, Liberini Federica > wrote: > Hello, > > I have estimated a random parameter conditional logit model, using the > command NLOGIT. > So far, I used the option ";Effects: x (*)" to obtain the elasticities > of choosing each model's alternative w.r.t to variable x. Is there a > way of obtaining standard errors for these elasticities? > I tried using the command "Partial Effects", but Limpdep returns the > error message saying that "Previous model did not store model setup > for PARTIALS.". > > Many Thanks, > Federica > > p.s.> here's a synthesis of the command I am using now > > nlogit; lhs=choice,nij,altcode > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US > ; model: U(AT,BE,BR,CA,CH,DE,DK,DOM,ES, > FI,FR,GB,IE,IT,NL,NO,RU,SE,US)= > FRb0,GBb0,IEb0,ITb0,NLb0,NOb0,RUb0,SEb0,0> + > FIoloc,FRoloc,GBoloc,IEoloc,IToloc,NLoloc,NOoloc,RUoloc,SEoloc,0> * X1 > + > > cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx>* X2 + > mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx>*Dumm1*X2 > + > > <0,0,0,0,0,0,0,domtx,0,0,0,0,0,0,0,0,0,0,0>*X2 + > <0,0,0,0,0,0,0,mndomtx,0,0,0,0,0,0,0,0,0,0,0>*Dumm1*X2 + > > ; fcn= cbtx(n) > ; rpl > ; maxit=400 > ; halton; pts=50 > ; alg=bfgs > ; effects: X2 (*) $ > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/q0YwBQfk2LenF9?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au From wgreene at stern.nyu.edu Mon Dec 4 22:45:42 2017 From: wgreene at stern.nyu.edu (William Greene) Date: Mon, 4 Dec 2017 06:45:42 -0500 Subject: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit In-Reply-To: <213F594826F3B9428143CEB7C51517E04C75566C@MBX23.d.ethz.ch> References: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> <213F594826F3B9428143CEB7C51517E04C753413@MBX23.d.ethz.ch> <213F594826F3B9428143CEB7C51517E04C75566C@MBX23.d.ethz.ch> Message-ID: Federica. Try ;FULL. I think that will generate output tables for the elasticities. /Bill On Mon, Dec 4, 2017 at 6:04 AM, Liberini Federica wrote: > Dear Bill, > > to check whether the issue was the syntax used for my estimation command, > I also estimated a simpler model specification, using this alternative > syntax: > > nlogit; lhs=choice,nij,altcode > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US > ;rhs=one,altstr > ;rh2=parstr > ;fcn=altstr(n) > ;checkdata > ;pds=3 > ;maxit=400 > ;alg=bfgs > ;pts=100; halton > ;effects:altstr(*) > ; ALL $ > > Once again, the elasticities are only displayed in the format of a matrix, > with no reported SE (see a partial pasted result below). Could the matter > be the version of my software (NLOGIT5)? > > Many thanks, > Federica > > > Elasticity wrt change of X in row choice on Prob[column choice] > --------+--------------------------------------------------- > -------------------- > ALTSTR | AT BE BR CA CH DE DK > DOM > --------+--------------------------------------------------- > -------------------- > AT| -.1779 .0005 .0005 .0005 .0005 .0005 .0005 > .0005 > BE| .0019 -.2309 .0019 .0019 .0019 .0019 .0019 > .0019 > BR| .0009 .0009 -.2436 .0009 .0009 .0009 .0009 > .0009 > CA| .0013 .0013 .0013 -.1318 .0013 .0013 .0013 > .0013 > CH| .0003 .0003 .0003 .0003 -.0613 .0003 .0003 > .0003 > DE| .0016 .0016 .0016 .0016 .0016 -.0974 .0016 > .0016 > DK| .0010 .0010 .0010 .0010 .0010 .0010 -.1756 > .0010 > DOM| .2932 .2932 .2932 .2932 .2932 .2932 .2932 > -.0569 > --------+--------------------------------------------------- > -------------------- > ALTSTR | ES FI FR GB IE IT NL > NO > --------+--------------------------------------------------- > -------------------- > AT|... > > > -----Original Message----- > From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of > Liberini Federica > Sent: 04 December 2017 10:25 > To: Limdep and Nlogit Mailing List > Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of > Random Parameter Conditional Logit > > Thank you very much for your reply. I have tried the "; ALL $" option at > the end of the command, but the output did not change for the version I got > without the "; ALL $" option. > > To be more precise, this is (a part of) the matrix of elasticities that I > get from the command shown earlier (augmented by the "; ALL $" option). > > > > Any other way of getting the Standard Errors of these elasticities? > > Many thanks > Federica > > > > > > Elasticity wrt change of X in row choice on Prob[column choice] > > --------+--------------------------------------------------- > -------------------- > > ALTSTR | AT BE BR CA CH DE DK > DOM > > --------+--------------------------------------------------- > -------------------- > > AT| -.4368 -.0122 -.0151 .0156 .0140 .0220 .0076 > .0043 > > BE| -.0454 2.3870 -.2807 .0040 .0154 .0243 -.0458 > .0045 > > BR| -.0504 -.1873 2.9656 -.0132 .0030 .0021 -.0501 > .0015 > > CA| .0320 -.0083 -.0130 -1.3293 .0569 .0628 .0320 > .0209 > > CH| .0096 .0027 .0018 .0154 -1.7195 .0182 .0095 > .0146 > > DE| .0628 .0166 .0077 .0921 .0996 -1.4425 .0623 > .0430 > > DK| .0135 -.0291 -.0354 .0310 .0286 .0380 -.3857 > .0088 > > DOM| -.0036 -.0018 -.0014 -.0055 -.0089 -.0070 -.0036 > .0006 > > --------+--------------------------------------------------- > -------------------- > > ALTSTR | ES FI FR GB IE IT NL > NO > > --------+--------------------------------------------------- > -------------------- > > AT| -.0038 .0057 -.0122 .0016 .0166 .0020 .0076 > .0016 > > BE| -.1400 -.0604 -.1697 -.0902 .0167 -.0880 -.0055 > -.0943 > > BR| -.1141 -.0602 -.1843 -.0866 .0005 -.0808 -.0486 > -.0840 > > CA| .0067 .0272 -.0076 .0209 .0634 .0191 .0303 > .0175 > > CH| .0047 .0084 .0049 .0069 .0209 .0067 .0092 > .0067 > > DE| .0302 .0549 .0219 .0468 .1068 .0442 .0631 > .0449 > > DK| -.0106 .0104 -.0266 .0051 .0339 .0010 .0147 > .0053 > > DOM| -.0025 -.0034 -.0022 -.0039 -.0076 -.0028 -.0039 > -.0030 > > --------+-------------------------- > > ALTSTR | RU SE US > > --------+-------------------------- > > AT... > > > > > > -----Original Message----- > From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of > William Greene > Sent: 01 December 2017 04:42 > To: Limdep and Nlogit Mailing List > Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of > Random Parameter Conditional Logit > > > > Federica. Try adding ;ALL to the command, to request the full set of > statistics for the elasticity. > > /Bill Greene > > > > On Mon, Nov 27, 2017 at 6:21 AM, Liberini Federica > > > wrote: > > > > > Hello, > > > > > > I have estimated a random parameter conditional logit model, using the > > > command NLOGIT. > > > So far, I used the option ";Effects: x (*)" to obtain the elasticities > > > of choosing each model's alternative w.r.t to variable x. Is there a > > > way of obtaining standard errors for these elasticities? > > > I tried using the command "Partial Effects", but Limpdep returns the > > > error message saying that "Previous model did not store model setup > > > for PARTIALS.". > > > > > > Many Thanks, > > > Federica > > > > > > p.s.> here's a synthesis of the command I am using now > > > > > > nlogit; lhs=choice,nij,altcode > > > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO, > RU,SE,US > > > ; model: U(AT,BE,BR,CA,CH,DE,DK,DOM,ES, > > > FI,FR,GB,IE,IT,NL,NO,RU,SE,US)= > > > > > FRb0,GBb0,IEb0,ITb0,NLb0,NOb0,RUb0,SEb0,0> + > > > > > FIoloc,FRoloc,GBoloc,IEoloc,IToloc,NLoloc,NOoloc,RUoloc,SEoloc,0> * X1 > > > + > > > > > > > > cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx>* X2 + > > > > > mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx>*Dumm1*X2 > > > + > > > > > > <0,0,0,0,0,0,0,domtx,0,0,0,0,0,0,0,0,0,0,0>*X2 + > > > <0,0,0,0,0,0,0,mndomtx,0,0,0,0,0,0,0,0,0,0,0>*Dumm1*X2 + > > > > > > ; fcn= cbtx(n) > > > ; rpl > > > ; maxit=400 > > > ; halton; pts=50 > > > ; alg=bfgs > > > ; effects: X2 (*) $ > > > > > > > > > _______________________________________________ > > > Limdep site list > > > Limdep at mailman.sydney.edu.au > > > http://limdep.itls.usyd.edu.au > > > > > > > > > > > > -- > > William Greene > > Department of Economics > > Stern School of Business, New York University > > 44 West 4 St., 7-90 > > New York, NY, 10012 > > URL: https://protect-au.mimecast.com/s/YZ5qB0ugdQgeuO?domain=people.stern.nyu.edu > > Email: wgreene at stern.nyu.edu > > Ph. +1.212.998.0876 > > Editor in Chief: Journal of Productivity Analysis Editor in Chief: > Foundations and Trends in Econometrics Associate Editor: Economics Letters > Associate Editor: Journal of Business and Economic Statistics Associate > Editor: Journal of Choice Modeling ______________________________ > _________________ > > Limdep site list > > Limdep at mailman.sydney.edu.au > > http://limdep.itls.usyd.edu.au > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/YZ5qB0ugdQgeuO?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling From liberini at kof.ethz.ch Tue Dec 5 01:12:15 2017 From: liberini at kof.ethz.ch (Liberini Federica) Date: Mon, 4 Dec 2017 14:12:15 +0000 Subject: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit In-Reply-To: References: <213F594826F3B9428143CEB7C51517E04C73A7E4@MBX13.d.ethz.ch> <213F594826F3B9428143CEB7C51517E04C753413@MBX23.d.ethz.ch> <213F594826F3B9428143CEB7C51517E04C75566C@MBX23.d.ethz.ch> Message-ID: <213F594826F3B9428143CEB7C51517E04C755AAC@MBX23.d.ethz.ch> Dear Bill, this now works perfectly with all different syntax. Many thanks! Federica -----Original Message----- From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf Of William Greene Sent: 04 December 2017 12:46 To: Limdep and Nlogit Mailing List Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of Random Parameter Conditional Logit Federica. Try ;FULL. I think that will generate output tables for the elasticities. /Bill On Mon, Dec 4, 2017 at 6:04 AM, Liberini Federica wrote: > Dear Bill, > > to check whether the issue was the syntax used for my estimation > command, I also estimated a simpler model specification, using this > alternative > syntax: > > nlogit; lhs=choice,nij,altcode > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO,RU,SE,US > ;rhs=one,altstr > ;rh2=parstr > ;fcn=altstr(n) > ;checkdata > ;pds=3 > ;maxit=400 > ;alg=bfgs > ;pts=100; halton > ;effects:altstr(*) > ; ALL $ > > Once again, the elasticities are only displayed in the format of a > matrix, with no reported SE (see a partial pasted result below). Could > the matter be the version of my software (NLOGIT5)? > > Many thanks, > Federica > > > Elasticity wrt change of X in row choice on Prob[column choice] > --------+--------------------------------------------------- > -------------------- > ALTSTR | AT BE BR CA CH DE DK > DOM > --------+--------------------------------------------------- > -------------------- > AT| -.1779 .0005 .0005 .0005 .0005 .0005 .0005 > .0005 > BE| .0019 -.2309 .0019 .0019 .0019 .0019 .0019 > .0019 > BR| .0009 .0009 -.2436 .0009 .0009 .0009 .0009 > .0009 > CA| .0013 .0013 .0013 -.1318 .0013 .0013 .0013 > .0013 > CH| .0003 .0003 .0003 .0003 -.0613 .0003 .0003 > .0003 > DE| .0016 .0016 .0016 .0016 .0016 -.0974 .0016 > .0016 > DK| .0010 .0010 .0010 .0010 .0010 .0010 -.1756 > .0010 > DOM| .2932 .2932 .2932 .2932 .2932 .2932 .2932 > -.0569 > --------+--------------------------------------------------- > -------------------- > ALTSTR | ES FI FR GB IE IT NL > NO > --------+--------------------------------------------------- > -------------------- > AT|... > > > -----Original Message----- > From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf > Of Liberini Federica > Sent: 04 December 2017 10:25 > To: Limdep and Nlogit Mailing List > Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of > Random Parameter Conditional Logit > > Thank you very much for your reply. I have tried the "; ALL $" option > at the end of the command, but the output did not change for the > version I got without the "; ALL $" option. > > To be more precise, this is (a part of) the matrix of elasticities > that I get from the command shown earlier (augmented by the "; ALL $" option). > > > > Any other way of getting the Standard Errors of these elasticities? > > Many thanks > Federica > > > > > > Elasticity wrt change of X in row choice on Prob[column choice] > > --------+--------------------------------------------------- > -------------------- > > ALTSTR | AT BE BR CA CH DE DK > DOM > > --------+--------------------------------------------------- > -------------------- > > AT| -.4368 -.0122 -.0151 .0156 .0140 .0220 .0076 > .0043 > > BE| -.0454 2.3870 -.2807 .0040 .0154 .0243 -.0458 > .0045 > > BR| -.0504 -.1873 2.9656 -.0132 .0030 .0021 -.0501 > .0015 > > CA| .0320 -.0083 -.0130 -1.3293 .0569 .0628 .0320 > .0209 > > CH| .0096 .0027 .0018 .0154 -1.7195 .0182 .0095 > .0146 > > DE| .0628 .0166 .0077 .0921 .0996 -1.4425 .0623 > .0430 > > DK| .0135 -.0291 -.0354 .0310 .0286 .0380 -.3857 > .0088 > > DOM| -.0036 -.0018 -.0014 -.0055 -.0089 -.0070 -.0036 > .0006 > > --------+--------------------------------------------------- > -------------------- > > ALTSTR | ES FI FR GB IE IT NL > NO > > --------+--------------------------------------------------- > -------------------- > > AT| -.0038 .0057 -.0122 .0016 .0166 .0020 .0076 > .0016 > > BE| -.1400 -.0604 -.1697 -.0902 .0167 -.0880 -.0055 > -.0943 > > BR| -.1141 -.0602 -.1843 -.0866 .0005 -.0808 -.0486 > -.0840 > > CA| .0067 .0272 -.0076 .0209 .0634 .0191 .0303 > .0175 > > CH| .0047 .0084 .0049 .0069 .0209 .0067 .0092 > .0067 > > DE| .0302 .0549 .0219 .0468 .1068 .0442 .0631 > .0449 > > DK| -.0106 .0104 -.0266 .0051 .0339 .0010 .0147 > .0053 > > DOM| -.0025 -.0034 -.0022 -.0039 -.0076 -.0028 -.0039 > -.0030 > > --------+-------------------------- > > ALTSTR | RU SE US > > --------+-------------------------- > > AT... > > > > > > -----Original Message----- > From: Limdep [mailto:limdep-bounces at mailman.sydney.edu.au] On Behalf > Of William Greene > Sent: 01 December 2017 04:42 > To: Limdep and Nlogit Mailing List > Subject: Re: [Limdep Nlogit List] Standard Errors for Elasticities of > Random Parameter Conditional Logit > > > > Federica. Try adding ;ALL to the command, to request the full set of > statistics for the elasticity. > > /Bill Greene > > > > On Mon, Nov 27, 2017 at 6:21 AM, Liberini Federica > > > > wrote: > > > > > Hello, > > > > > > I have estimated a random parameter conditional logit model, using > > the > > > command NLOGIT. > > > So far, I used the option ";Effects: x (*)" to obtain the > > elasticities > > > of choosing each model's alternative w.r.t to variable x. Is there a > > > way of obtaining standard errors for these elasticities? > > > I tried using the command "Partial Effects", but Limpdep returns the > > > error message saying that "Previous model did not store model setup > > > for PARTIALS.". > > > > > > Many Thanks, > > > Federica > > > > > > p.s.> here's a synthesis of the command I am using now > > > > > > nlogit; lhs=choice,nij,altcode > > > ; choices=AT,BE,BR,CA,CH,DE,DK,DOM,ES,FI,FR,GB,IE,IT,NL,NO, > RU,SE,US > > > ; model: U(AT,BE,BR,CA,CH,DE,DK,DOM,ES, > > > FI,FR,GB,IE,IT,NL,NO,RU,SE,US)= > > > > > FRb0,GBb0,IEb0,ITb0,NLb0,NOb0,RUb0,SEb0,0> + > > > > > FIoloc,FRoloc,GBoloc,IEoloc,IToloc,NLoloc,NOoloc,RUoloc,SEoloc,0> * > > X1 > > > + > > > > > > > > cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx,cbtx>* X2 + > > > > > mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx,mcbtx>*Dumm1*X > > 2 > > > + > > > > > > <0,0,0,0,0,0,0,domtx,0,0,0,0,0,0,0,0,0,0,0>*X2 + > > > <0,0,0,0,0,0,0,mndomtx,0,0,0,0,0,0,0,0,0,0,0>*Dumm1*X2 + > > > > > > ; fcn= cbtx(n) > > > ; rpl > > > ; maxit=400 > > > ; halton; pts=50 > > > ; alg=bfgs > > > ; effects: X2 (*) $ > > > > > > > > > _______________________________________________ > > > Limdep site list > > > Limdep at mailman.sydney.edu.au > > > http://limdep.itls.usyd.edu.au > > > > > > > > > > > > -- > > William Greene > > Department of Economics > > Stern School of Business, New York University > > 44 West 4 St., 7-90 > > New York, NY, 10012 > > URL: https://protect-au.mimecast.com/s/W91ABZiLAeKxTX?domain=people.stern.nyu.edu > > Email: wgreene at stern.nyu.edu > > Ph. +1.212.998.0876 > > Editor in Chief: Journal of Productivity Analysis Editor in Chief: > Foundations and Trends in Econometrics Associate Editor: Economics > Letters Associate Editor: Journal of Business and Economic Statistics > Associate > Editor: Journal of Choice Modeling ______________________________ > _________________ > > Limdep site list > > Limdep at mailman.sydney.edu.au > > http://limdep.itls.usyd.edu.au > > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics Stern School of Business, New York University 44 West 4 St., 7-90 New York, NY, 10012 URL: https://protect-au.mimecast.com/s/W91ABZiLAeKxTX?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.212.998.0876 Editor in Chief: Journal of Productivity Analysis Editor in Chief: Foundations and Trends in Econometrics Associate Editor: Economics Letters Associate Editor: Journal of Business and Economic Statistics Associate Editor: Journal of Choice Modeling _______________________________________________ Limdep site list Limdep at mailman.sydney.edu.au http://limdep.itls.usyd.edu.au