From john.c.whitehead at gmail.com Thu Sep 3 02:29:07 2020 From: john.c.whitehead at gmail.com (John C. Whitehead) Date: Wed, 2 Sep 2020 12:29:07 -0400 Subject: [Limdep Nlogit List] SALC models in NLOGIT? In-Reply-To: <5F471450.9090502@sydney.edu.au> References: <5F471450.9090502@sydney.edu.au> Message-ID: Is it possible to parameterize the scale in a latent class model (e.g., RP/SP) like in the GMXL? On Wed, Aug 26, 2020 at 10:03 PM David Hensher via Limdep < limdep at mailman.sydney.edu.au> wrote: > See attached from our 2015 edition of ACA which you might purchase. > > David > On 27/08/2020 11:49 AM, Jason Ong via Limdep wrote: > > hi, > > > > Is there the possibility to run scale-adjusted latent class models in > > NLOGIT? > > if not, will there be plans to do so? > > thank for your help > > > > Best, > > > > > > *Jason Ong* > > Twitter: @DrJasonJOng > > PhD, MMed, MBBS, FAChSHM, FRACGP > > > > Sexual Health Physician, Melbourne Sexual Health Centre, Alfred Health > > Associate Professor (Hon), London School of Hygiene and Tropical > Medicine, > > UK > > Central Clinical School, Monash University, Australia > > Melbourne School of Population and Global Health, University of > Melbourne, > > Australia > > Associate Editor, Sexually Transmitted Infections > > Special Issues Editor, Sexual Health > > Board Director, ASHM (https://protect-au.mimecast.com/s/cPCmCL7EwMf38xEAIBEkcB?domain=ashm.org.au) > > https://protect-au.mimecast.com/s/io3ZCMwGxOtJmKEgSkKnM7?domain=lshtm.ac.uk > > https://protect-au.mimecast.com/s/Hd7ECNLJyQU6yKvAcjGY6l?domain=researchgate.net > > _______________________________________________ > > Limdep site list > > Limdep at mailman.sydney.edu.au > > http://limdep.itls.usyd.edu.au > > > > > > > -- > DAVID HENSHER FASSA, PhD| Professor and Founding Director > Institute of Transport and Logistics Studies | The University of Sydney > Business School > > THE UNIVERSITY OF SYDNEY > Rm 201, Building H73| The University of Sydney | NSW | 2006 > Street Address: 378 Abercrombie St, Darlington NSW 2008 > T +61 2 9114 1871 | F +61 2 9114 1863 | M +61 418 433 057 > E David.Hensher at sydney.edu.au | W sydney.edu.au/business/itls |W > http://sydney.edu.au/business/itls/staff/davidh > > Celebrating 30 years of ITLS: 1991-2020 https://protect-au.mimecast.com/s/XZ8DCOMKzVTOQVqJIrQrXE?domain=youtu.be > ERA Rank 5 (Transportation and Freight Services) > Co-Founder of the International Conference Series on Competition and > Ownership of Land Passenger Transport (The 'Thredbo' Series) > https://protect-au.mimecast.com/s/tXO-CP7LAXf6VYyOc6i2gk?domain=thredbo-conference-series.org > https://www.linkedin.com/company/28450714 > Second edition of Applied Choice Analysis now available at > https://protect-au.mimecast.com/s/MQtPCQnMBZfRZGz8TAj3jF?domain=cambridge.org > Nlogit is the most popular software for choice modellers. See > https://protect-au.mimecast.com/s/zw1ICROND2uOZ97JIQLWG6?domain=limdep.com > CRICOS 00026A > This email plus any attachments to it are confidential. Any unauthorised > use is strictly prohibited. If you receive this email in error, please > delete it and any attachments. > > Please think of our environment and only print this e-mail if necessary. > > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > From Thao.T.Thai at monash.edu Fri Sep 11 10:44:19 2020 From: Thao.T.Thai at monash.edu (Thao Thai) Date: Fri, 11 Sep 2020 10:44:19 +1000 Subject: [Limdep Nlogit List] ASCs calibration Message-ID: Hi Nlogit users, Train's textbook (2000) page 75 pointed out that when using the results from SP for simulations, ASCs should be calibrated to the actual shares of alternatives. (1) I followed Train's suggestion to adjust ASCs to new values and run the syntax below, the coefficients are different from the coefficients obtained from the original SP. I guess it is not the correct way to do ASCs calibration? |-> sample;all$ |-> Nlogit ;lhs = cho, cset, alti ;choices = H, C, P, I, G, N ;Alg=BFGS ;checkdata ;model: U(H) = rl_h1 * RL_H1 + rl_h2 * RL_H2 + fl_ * FL_H + cr_h1 * CR_H1 + cr_2 * CR_H2 + lo_h1 * LO_H1 + sa_ * SA_H / U(C) = com[0.960] + rl_c1 * RL_C1 + rl_c2 * RL_C2 + fl_ * FL_C + cr_c1 * CR_C1 + cr_2 * CR_C2 + lo_c1 * LO_C1 + lo_c2 * LO_C2 + sa_ * SA_C/ U(P) = pri[-1.225] + rl_p1 * RL_P1 + fl_ * FL_P + cr_p1 * CR_P1 + cr_2 * CR_P2 + lo_p1 * LO_P1 + lo_p2 * LO_P2 + sa_ * SA_P/ U(I) = ind[-2.440] + rl_i1 * RL_I1 + rl_i2 * RL_I2 + fl_ * FL_I + cr_i1 * CR_I1 + lo_i1 * LO_I1 + sa_ * SA_I/ U(G) = gov[-0.548] + rl_g1 * RL_G1 + fl_ * FL_G + cr_g1 * CR_G1 + lo_g1 * LO_G1 + sa_ * SA_G/ U(N) = non[-0.844] + rl_n1 * RL_N1 + fl_ * FL_N + cr_n1 * CR_N1 + lo_n1 * LO_N1 + lo_n2 * LO_N2 + sa_ * SA_N $ (2) I then used the endogenous weighting to the SP model, the coefficient results are different from the original SP model. I guess this way is not correct either. |-> sample;all$ |-> Nlogit ;lhs = cho, cset, alti ;choices = H, C, P, I, G, N/0.242,0.5134,0.0388,0.0468,0.0922,0.0668 ;Alg=BFGS ;checkdata ;model: U(H) = rl_h1 * RL_H1 + rl_h2 * RL_H2 + fl_ * FL_H + cr_h1 * CR_H1 + cr_2 * CR_H2 + lo_h1 * LO_H1 + sa_ * SA_H / U(C) = com + rl_c1 * RL_C1 + rl_c2 * RL_C2 + fl_ * FL_C + cr_c1 * CR_C1 + cr_2 * CR_C2 + lo_c1 * LO_C1 + lo_c2 * LO_C2 + sa_ * SA_C/ U(P) = pri + rl_p1 * RL_P1 + fl_ * FL_P + cr_p1 * CR_P1 + cr_2 * CR_P2 + lo_p1 * LO_P1 + lo_p2 * LO_P2 + sa_ * SA_P/ U(I) = ind + rl_i1 * RL_I1 + rl_i2 * RL_I2 + fl_ * FL_I + cr_i1 * CR_I1 + lo_i1 * LO_I1 + sa_ * SA_I/ U(G) = gov + rl_g1 * RL_G1 + fl_ * FL_G + cr_g1 * CR_G1 + lo_g1 * LO_G1 + sa_ * SA_G/ U(N) = non + rl_n1 * RL_N1 + fl_ * FL_N + cr_n1 * CR_N1 + lo_n1 * LO_N1 + lo_n2 * LO_N2 + sa_ * SA_N $ (3) I then run a model with fixed coefficient estimates but ASCs with endogenous weighting. The ASCs estimates are similar to the adjusted ASCs in step (1) as per suggestion of Train (2000). However, the base shares are not the same as the shares that I specified in the model |-> sample;all$ |-> Nlogit ;lhs = cho, cset, alti ;choices = H, C, P, I, G, N/0.241,0.5153,0.0386,0.0466,0.0919,0.0666 ;checkdata ;show 'Alg=BFGS ;calibrate ;model: U(H) = rl_h1[0.0700481] * RL_H1 + rl_h2[0.231038] * RL_H2 + fl_[0.178665] * FL_H + cr_h1[0.271042] * CR_H1 + cr_2[0.0529584] * CR_H2 + lo_h1[-0.414659] * LO_H1 + sa_[0.0123069] * SA_H / U(C) = com + rl_c1[0.387869] * RL_C1 + rl_c2[0.263637] * RL_C2 + fl_[0.178665] * FL_C + cr_c1[0.19661] * CR_C1 + cr_2[0.0529584] * CR_C2 + lo_c1[-0.222456] * LO_C1 + lo_c2[-0.820609] * LO_C2 + sa_[0.0123069] * SA_C / U(P) = pri + rl_p1[0.0167174] * RL_P1 + fl_[0.178665] * FL_P + cr_p1[0.333571] * CR_P1 + cr_2[0.0529584] * CR_P2 + lo_p1[-0.951557] * LO_P1 + lo_p2[-1.03276] * LO_P2 + sa_[0.0123069] * SA_P / U(I) = ind + rl_i1[0.643119] * RL_I1 + rl_i2[0.790318] * RL_I2 + fl_[0.178665] * FL_I + cr_i1[0.610239] * CR_I1 + lo_i1[-0.64615] * LO_I1 + sa_[0.0123069] * SA_I / U(G) = gov + rl_g1[-0.331743] * RL_G1 + fl_[0.178665] * FL_G + cr_g1[0.516844] * CR_G1 + lo_g1[-0.57783] * LO_G1 + sa_[0.0123069] * SA_G / U(N) = non + rl_n1[-0.0814267] * RL_N1 + fl_[0.178665] * FL_N + cr_n1[0.36292] * CR_N1 + lo_n1[-0.585064] * LO_N1 + lo_n2[-0.466387] * LO_N2 + sa_[0.0123069] * SA_N$ The base share results below +----------+--------------+--------------+------------------+ |Choice | Base | Scenario | Scenario - Base | | |%Share Number |%Share Number |ChgShare ChgNumber| +----------+--------------+--------------+------------------+ |H | 24.823 604 | 22.801 555 | -2.023% -49 | |C | 48.452 1179 | 52.560 1279 | 4.108% 100 | |P | 4.596 112 | 4.208 102 | -.388% -10 | |I | 5.192 126 | 4.804 117 | -.388% -9 | |G | 9.971 243 | 9.150 223 | -.820% -20 | |N | 6.965 170 | 6.476 158 | -.489% -12 | |Total |100.000 2434 |100.000 2434 | .000% 0 | +----------+--------------+--------------+------------------+ Question: (1) Could you kindly please let me know how I should calibrate ASCs in simulation in Nlogit? (2) I'd like to do the simulation using a Mixed logit with all ASCs being random parameters. Please let me know if there are any special considerations when calibrating ASCs. Thank you so much. I truly look forward to your help. Best regards, Thao -- *Thao Thai*| MHEcon(Adv), BPharm PhD candidate Centre for Health Economics Monash Business School | Monash University Tel (03) 99029847| Thao.T.Thai at monash.edu From Thao.T.Thai at monash.edu Fri Sep 11 11:48:10 2020 From: Thao.T.Thai at monash.edu (Thao Thai) Date: Fri, 11 Sep 2020 11:48:10 +1000 Subject: [Limdep Nlogit List] Question about export WTPs results Message-ID: Hi Nlogit, Could I export the WTPs results calculated using the WALD command? The export command seems only to export the coefficient estimates only. Please correct me if I am wrong. Thank you so much for your help. Thank you so much. Thao -- *Thao Thai*| MHEcon(Adv), BPharm PhD candidate Centre for Health Economics Monash Business School | Monash University Tel (03) 99029847| Thao.T.Thai at monash.edu From wgreene at stern.nyu.edu Sat Sep 12 04:32:01 2020 From: wgreene at stern.nyu.edu (William Greene) Date: Fri, 11 Sep 2020 14:32:01 -0400 Subject: [Limdep Nlogit List] ASCs calibration In-Reply-To: References: Message-ID: Train's suggestion would apply if you are using an MNL fit on one sample to simulate the data from a different sample. That does not appear to be the case in your application. You don't need to calibrate the ASCs when you estimate the model and simulate the data used to do the estimation. The ASCs are calibrated by the FOCs of the ML estimation. /B. Greene On Thu, Sep 10, 2020 at 8:45 PM Thao Thai via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi Nlogit users, > > Train's textbook (2000) page 75 pointed out that when using the results > from SP for simulations, ASCs should be calibrated to the actual shares of > alternatives. > (1) I followed Train's suggestion to adjust ASCs to new values and run the > syntax below, the coefficients are different from the coefficients > obtained from the original SP. I guess it is not the correct way to do ASCs > calibration? > |-> sample;all$ > |-> Nlogit > ;lhs = cho, cset, alti > ;choices = H, C, P, I, G, N > ;Alg=BFGS > ;checkdata > ;model: > U(H) = rl_h1 * RL_H1 + rl_h2 * RL_H2 > + fl_ * FL_H > + cr_h1 * CR_H1 + cr_2 * CR_H2 > + lo_h1 * LO_H1 > + sa_ * SA_H > / > U(C) = com[0.960] > + rl_c1 * RL_C1 + rl_c2 * RL_C2 > + fl_ * FL_C > + cr_c1 * CR_C1 + cr_2 * CR_C2 > + lo_c1 * LO_C1 + lo_c2 * LO_C2 > + sa_ * SA_C/ > U(P) = pri[-1.225] > + rl_p1 * RL_P1 > + fl_ * FL_P > + cr_p1 * CR_P1 + cr_2 * CR_P2 > + lo_p1 * LO_P1 + lo_p2 * LO_P2 > + sa_ * SA_P/ > U(I) = ind[-2.440] > + rl_i1 * RL_I1 + rl_i2 * RL_I2 > + fl_ * FL_I > + cr_i1 * CR_I1 > + lo_i1 * LO_I1 > + sa_ * SA_I/ > U(G) = gov[-0.548] > + rl_g1 * RL_G1 > + fl_ * FL_G > + cr_g1 * CR_G1 > + lo_g1 * LO_G1 > + sa_ * SA_G/ > U(N) = non[-0.844] > + rl_n1 * RL_N1 > + fl_ * FL_N > + cr_n1 * CR_N1 > + lo_n1 * LO_N1 + lo_n2 * LO_N2 > + sa_ * SA_N > $ > (2) I then used the endogenous weighting to the SP model, the coefficient > results are different from the original SP model. I guess this way is not > correct either. > > |-> sample;all$ > |-> Nlogit > ;lhs = cho, cset, alti > ;choices = H, C, P, I, G, N/0.242,0.5134,0.0388,0.0468,0.0922,0.0668 > ;Alg=BFGS > ;checkdata > ;model: > U(H) = rl_h1 * RL_H1 + rl_h2 * RL_H2 > + fl_ * FL_H > + cr_h1 * CR_H1 + cr_2 * CR_H2 > + lo_h1 * LO_H1 > + sa_ * SA_H > / > U(C) = com > + rl_c1 * RL_C1 + rl_c2 * RL_C2 > + fl_ * FL_C > + cr_c1 * CR_C1 + cr_2 * CR_C2 > + lo_c1 * LO_C1 + lo_c2 * LO_C2 > + sa_ * SA_C/ > U(P) = pri > + rl_p1 * RL_P1 > + fl_ * FL_P > + cr_p1 * CR_P1 + cr_2 * CR_P2 > + lo_p1 * LO_P1 + lo_p2 * LO_P2 > + sa_ * SA_P/ > U(I) = ind > + rl_i1 * RL_I1 + rl_i2 * RL_I2 > + fl_ * FL_I > + cr_i1 * CR_I1 > + lo_i1 * LO_I1 > + sa_ * SA_I/ > U(G) = gov > + rl_g1 * RL_G1 > + fl_ * FL_G > + cr_g1 * CR_G1 > + lo_g1 * LO_G1 > + sa_ * SA_G/ > U(N) = non > + rl_n1 * RL_N1 > + fl_ * FL_N > + cr_n1 * CR_N1 > + lo_n1 * LO_N1 + lo_n2 * LO_N2 > + sa_ * SA_N > $ > (3) I then run a model with fixed coefficient estimates but ASCs with > endogenous weighting. The ASCs estimates are similar to the adjusted ASCs > in step (1) as per suggestion of Train (2000). However, the base shares are > not the same as the shares that I specified in the model > |-> sample;all$ > |-> Nlogit > ;lhs = cho, cset, alti > ;choices = H, C, P, I, G, N/0.241,0.5153,0.0386,0.0466,0.0919,0.0666 > ;checkdata > ;show > 'Alg=BFGS > ;calibrate > ;model: > U(H) = rl_h1[0.0700481] * RL_H1 + rl_h2[0.231038] * RL_H2 > + fl_[0.178665] * FL_H > + cr_h1[0.271042] * CR_H1 + cr_2[0.0529584] * CR_H2 > + lo_h1[-0.414659] * LO_H1 > + sa_[0.0123069] * SA_H > / > U(C) = com > + rl_c1[0.387869] * RL_C1 + rl_c2[0.263637] * RL_C2 > + fl_[0.178665] * FL_C > + cr_c1[0.19661] * CR_C1 + cr_2[0.0529584] * CR_C2 > + lo_c1[-0.222456] * LO_C1 + lo_c2[-0.820609] * LO_C2 > + sa_[0.0123069] * SA_C > / > U(P) = pri > + rl_p1[0.0167174] * RL_P1 > + fl_[0.178665] * FL_P > + cr_p1[0.333571] * CR_P1 + cr_2[0.0529584] * CR_P2 > + lo_p1[-0.951557] * LO_P1 + lo_p2[-1.03276] * LO_P2 > + sa_[0.0123069] * SA_P > / > U(I) = ind > + rl_i1[0.643119] * RL_I1 + rl_i2[0.790318] * RL_I2 > + fl_[0.178665] * FL_I > + cr_i1[0.610239] * CR_I1 > + lo_i1[-0.64615] * LO_I1 > + sa_[0.0123069] * SA_I > / > U(G) = gov > + rl_g1[-0.331743] * RL_G1 > + fl_[0.178665] * FL_G > + cr_g1[0.516844] * CR_G1 > + lo_g1[-0.57783] * LO_G1 > + sa_[0.0123069] * SA_G > / > U(N) = non > + rl_n1[-0.0814267] * RL_N1 > + fl_[0.178665] * FL_N > + cr_n1[0.36292] * CR_N1 > + lo_n1[-0.585064] * LO_N1 + lo_n2[-0.466387] * LO_N2 > + sa_[0.0123069] * SA_N$ > The base share results below > +----------+--------------+--------------+------------------+ > |Choice | Base | Scenario | Scenario - Base | > | |%Share Number |%Share Number |ChgShare ChgNumber| > +----------+--------------+--------------+------------------+ > |H | 24.823 604 | 22.801 555 | -2.023% -49 | > |C | 48.452 1179 | 52.560 1279 | 4.108% 100 | > |P | 4.596 112 | 4.208 102 | -.388% -10 | > |I | 5.192 126 | 4.804 117 | -.388% -9 | > |G | 9.971 243 | 9.150 223 | -.820% -20 | > |N | 6.965 170 | 6.476 158 | -.489% -12 | > |Total |100.000 2434 |100.000 2434 | .000% 0 | > +----------+--------------+--------------+------------------+ > > Question: (1) Could you kindly please let me know how I should calibrate > ASCs in simulation in Nlogit? > (2) I'd like to do the simulation using a Mixed logit with > all ASCs being random parameters. Please let me know if there are any > special considerations when calibrating ASCs. > > Thank you so much. I truly look forward to your help. > Best regards, > Thao > > > -- > *Thao Thai*| MHEcon(Adv), BPharm > PhD candidate > Centre for Health Economics > Monash Business School | Monash University > Tel (03) 99029847| Thao.T.Thai at monash.edu > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics, emeritus Stern School of Business, New York University 44 West 4 St. New York, NY, 10012 URL: https://protect-au.mimecast.com/s/oKQYCq71mwfvNP2XUXkZla?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.646.596.3296 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 From Thao.T.Thai at monash.edu Thu Sep 17 14:13:22 2020 From: Thao.T.Thai at monash.edu (Thao Thai) Date: Thu, 17 Sep 2020 14:13:22 +1000 Subject: [Limdep Nlogit List] WTP-space MNL model syntax Message-ID: Dear Nlogit users, Background: I have two DCE designs differing in one design dimension. I want to test whether there is a difference in WTPs results between two designs. As such, I want to run a WTP-space MNL including interactions between a dummy for design type and WTP values of each attribute. My issue: Nlogit manual provides instructions on how to run WTP-space for Mixed logit models. Could you please kindly give me some advice on the syntax to run a WTP-space MNL model? or some suggestions on another way to deal with my issue if possible please? Thank you so much for your help. Best regards, Thao From david.hensher at sydney.edu.au Thu Sep 17 14:28:07 2020 From: david.hensher at sydney.edu.au (David Hensher) Date: Thu, 17 Sep 2020 14:28:07 +1000 Subject: [Limdep Nlogit List] WTP-space MNL model syntax In-Reply-To: References: Message-ID: <5F62E5D7.8050101@sydney.edu.au> It is really set up for a mixed logit model. While I cannot guarantee your model would work, you can implement a useful trick by choosing one parameter and setting it as nonstochastic. For example: ?Add into command stream ;rpl; fcn=x(c) ?x is any variable you can choose ?optional ;halton,pts=20$ David On 17/09/2020 2:13 PM, Thao Thai via Limdep wrote: > Dear Nlogit users, > > Background: I have two DCE designs differing in one design dimension. I > want to test whether there is a difference in WTPs results between two > designs. As such, I want to run a WTP-space MNL including interactions > between a dummy for design type and WTP values of each attribute. > > My issue: Nlogit manual provides instructions on how to run WTP-space for > Mixed logit models. Could you please kindly give me some advice on > the syntax to run a WTP-space MNL model? or some suggestions on another way > to deal with my issue if possible please? > > Thank you so much for your help. > Best regards, > Thao > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- DAVID HENSHER FASSA, PhD| Professor and Founding Director Institute of Transport and Logistics Studies | The University of Sydney Business School THE UNIVERSITY OF SYDNEY Rm 450, Merewether Building H04| The University of Sydney | NSW | 2006 Street Address: Butlin Ave, Darlington NSW 2008 T +61 2 9114 1871 | F +61 2 9114 1863 | M +61 418 433 057 E David.Hensher at sydney.edu.au | W sydney.edu.au/business/itls |W http://sydney.edu.au/business/itls/staff/davidh Celebrating 30 years of ITLS: 1991-2020 https://protect-au.mimecast.com/s/ZLFICJyBrGf9PN6jfVHNn9?domain=youtu.be ERA Rank 5 (Transportation and Freight Services) Co-Founder of the International Conference Series on Competition and Ownership of Land Passenger Transport (The 'Thredbo' Series) https://protect-au.mimecast.com/s/qvDOCK1DvKT70VXRSvCrfA?domain=thredbo-conference-series.org https://www.linkedin.com/company/28450714 Second edition of Applied Choice Analysis now available at https://protect-au.mimecast.com/s/stB1CL7EwMfB56GziPZDXl?domain=cambridge.org Nlogit is the most popular software for choice modellers. See https://protect-au.mimecast.com/s/A6q3CMwGxOtBGNwniWiRV9?domain=limdep.com CRICOS 00026A This email plus any attachments to it are confidential. Any unauthorised use is strictly prohibited. If you receive this email in error, please delete it and any attachments. Please think of our environment and only print this e-mail if necessary. From wgreene at stern.nyu.edu Fri Sep 18 01:41:49 2020 From: wgreene at stern.nyu.edu (William Greene) Date: Thu, 17 Sep 2020 11:41:49 -0400 Subject: [Limdep Nlogit List] WTP-space MNL model syntax In-Reply-To: References: Message-ID: Thao. In the MNL, not mixed logit, the WTP space is a one to one transformation of the original parameters. You would get the identical answer for WTP whether you use the MNL and take the ratio of estimates or you use the WTP space parameterization. This construction is unnecessary. /Bill Greene On Thu, Sep 17, 2020 at 12:14 AM Thao Thai via Limdep < limdep at mailman.sydney.edu.au> wrote: > Dear Nlogit users, > > Background: I have two DCE designs differing in one design dimension. I > want to test whether there is a difference in WTPs results between two > designs. As such, I want to run a WTP-space MNL including interactions > between a dummy for design type and WTP values of each attribute. > > My issue: Nlogit manual provides instructions on how to run WTP-space for > Mixed logit models. Could you please kindly give me some advice on > the syntax to run a WTP-space MNL model? or some suggestions on another way > to deal with my issue if possible please? > > Thank you so much for your help. > Best regards, > Thao > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics, emeritus Stern School of Business, New York University 44 West 4 St. New York, NY, 10012 URL: https://protect-au.mimecast.com/s/CdWBCJyBrGf903mPfVRKk8?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.646.596.3296 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 From Thao.T.Thai at monash.edu Fri Sep 18 10:45:36 2020 From: Thao.T.Thai at monash.edu (Thao Thai) Date: Fri, 18 Sep 2020 10:45:36 +1000 Subject: [Limdep Nlogit List] WTP-space MNL model syntax In-Reply-To: References: Message-ID: Dear Professor Greene, Thank you so much for your help so far. I truly appreciate it. I understand what you mean by running the MNL and taking the ratio of coefficients to get WTP values. The issue is by calculating WTPs, I am not able to do statistical testing on the WTPs results. Further, statistical testing on a preference-pace MNL will have the scale issue resulted from two different data sets. Are there any ways that I can test if WTPs from two data sets are statistically (in)significantly different using Nlogit? I would really appreciate any suggestions. Thank you so much! Best regards, Thao On Fri, 18 Sep 2020 at 01:42, William Greene via Limdep < limdep at mailman.sydney.edu.au> wrote: > Thao. In the MNL, not mixed logit, the WTP space is a one to one > transformation > of the original parameters. You would get the identical answer for WTP > whether you > use the MNL and take the ratio of estimates or you use the WTP space > parameterization. > This construction is unnecessary. > /Bill Greene > > On Thu, Sep 17, 2020 at 12:14 AM Thao Thai via Limdep < > limdep at mailman.sydney.edu.au> wrote: > > > Dear Nlogit users, > > > > Background: I have two DCE designs differing in one design dimension. I > > want to test whether there is a difference in WTPs results between two > > designs. As such, I want to run a WTP-space MNL including interactions > > between a dummy for design type and WTP values of each attribute. > > > > My issue: Nlogit manual provides instructions on how to run WTP-space for > > Mixed logit models. Could you please kindly give me some advice on > > the syntax to run a WTP-space MNL model? or some suggestions on another > way > > to deal with my issue if possible please? > > > > Thank you so much for your help. > > Best regards, > > Thao > > _______________________________________________ > > Limdep site list > > Limdep at mailman.sydney.edu.au > > http://limdep.itls.usyd.edu.au > > > > > > -- > William Greene > Department of Economics, emeritus > Stern School of Business, New York University > 44 West 4 St. > New York, NY, 10012 > URL: https://protect-au.mimecast.com/s/ZrhoCgZ0N1iE0G2XcNyiZN?domain=people.stern.nyu.edu > Email: wgreene at stern.nyu.edu > Ph. +1.646.596.3296 > Editor in Chief: Journal of Productivity Analysis > < > https://protect-au.mimecast.com/s/57ICCjZ1N7io5RqLcRyi-F?domain=springer.com > > > < > https://protect-au.mimecast.com/s/57ICCjZ1N7io5RqLcRyi-F?domain=springer.com > > > Editor in Chief: Foundations and Trends in Econometrics > Associate Editor: Economics Letters > Associate Editor: Journal of Business and Economic Statistics > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- *Thao Thai*| MHEcon(Adv), BPharm PhD candidate Centre for Health Economics Monash Business School | Monash University Tel (03) 99029847| Thao.T.Thai at monash.edu From Thao.T.Thai at monash.edu Mon Sep 21 11:36:09 2020 From: Thao.T.Thai at monash.edu (Thao Thai) Date: Mon, 21 Sep 2020 11:36:09 +1000 Subject: [Limdep Nlogit List] Error 668: Error: N not a multiple of T Message-ID: Hi Nlogit user, In my data set, each respondent answered 4 DCE questions with 3 alternatives and 3 DCE questions with 6 alternatives. To run the scaled MNL model, I specified: ;pds=7 but I got the error message: "Error 668: Error: N not a multiple of T. N= 23700. T= 7" I understand N is the total lines in the data: 790 * (4*3 + 3*6) = 23700 which is obviously not a multiple of 7. However, each respondent does make 7 choices. Could you please let me know how I should make it right? Thank you so much. Best regards, Thao From wgreene at stern.nyu.edu Mon Sep 21 21:18:04 2020 From: wgreene at stern.nyu.edu (William Greene) Date: Mon, 21 Sep 2020 07:18:04 -0400 Subject: [Limdep Nlogit List] Error 668: Error: N not a multiple of T In-Reply-To: References: Message-ID: Thao. If you have specified the LHS variables correctly for choice models with differing sized choice sets, then the appropriate number of periods for the PDS specification is the number of choices, which is 7, as you did. The error 668 occurs before nlogit has resolved that this is a choice model, not an ordinary panel. In that case, the processing continues on to the choice model, where PDS=7 is correct. So, you can treat the 668 error as a warning. The data are organized properly. Resolution of the data setup takes two steps. The warning takes place at the first, where nlogit is just counting the rows of data. /Bill Greene On Sun, Sep 20, 2020 at 9:37 PM Thao Thai via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi Nlogit user, > > In my data set, each respondent answered 4 DCE questions with 3 > alternatives and 3 DCE questions with 6 alternatives. To run the scaled MNL > model, I specified: ;pds=7 but I got the error message: > > "Error 668: Error: N not a multiple of T. N= 23700. T= 7" > > I understand N is the total lines in the data: 790 * (4*3 + 3*6) = 23700 > which is obviously not a multiple of 7. However, each respondent does make > 7 choices. > > Could you please let me know how I should make it right? Thank you so much. > > Best regards, > Thao > _______________________________________________ > Limdep site list > Limdep at mailman.sydney.edu.au > http://limdep.itls.usyd.edu.au > > -- William Greene Department of Economics, emeritus Stern School of Business, New York University 44 West 4 St. New York, NY, 10012 URL: https://protect-au.mimecast.com/s/7ScjCyojxQTOoxx0FZ9Roa?domain=people.stern.nyu.edu Email: wgreene at stern.nyu.edu Ph. +1.646.596.3296 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