From thames_k at yahoo.com Fri Mar 6 11:35:36 2020 From: thames_k at yahoo.com (Thamarasi Kularatne) Date: Fri, 6 Mar 2020 00:35:36 +0000 (UTC) Subject: [Limdep Nlogit List] GMXL (WTP space) in Nlogit References: <499292086.438801.1583454936741.ref@mail.yahoo.com> Message-ID: <499292086.438801.1583454936741@mail.yahoo.com> Hi, I'm trying to run a generalised mixed logit model (GMXL) in WTP space in order to account for taste and scale heterogeneity. As explained in the Nlogit 6 reference guide, we can choose one of the parameters in the GMXLOGIT model to have a coefficient of one and build this nonlinearity into the GMXLOGIT model by changing its type to (*type) in the ; Fcn = (*type),? specification. In my case, I have 3 alternatives and the cost parameters need to be alternative specific. Therefore when estimating GMXL in WTP space, I need to specify 3 fixed parameters. example below: GMXlogit ;userp ;lhs=choice,cset,altij ;choices=oral,inject,infuse,none ;pds=9 ;halton ;pts=10 ;fcn=ocost(*n),icost(*n),ivcost(*n),eff(n),mild(n),inj_6m(n),spec(n) ;par ;pwt ;gmx ;cor ;gamma=0 ;tau=0.1 ;Model: U(oral)=eff*eff+ oral_wee*oral_wee + oral_m*oral_mon + mild*mild_se + sev2*sev_2 + ocost*oralcost+ spec*spec+ oself*oral_sel / U(inject)=inject+eff*eff+ inj_w*inj_week + inj_m*inj_mon + inj_6m*inj_6mon + inj_y*inj_yr + mild*mild_se + sev2*sev_2+ icost*injcost+ spec*spec+iadmin*admin_in / U(infuse)=infuse+ eff*eff+ mild*mild_se + sev2*sev_2+ivcost*ivcost+ iv_6m*iv_6mon + iv_yr*iv_yr + spec*spec + ivadmin*admin_iv/ U(none)=None $ This does not work. Nlogit only takes one parameter at a time with a * in the fcn specification. Is there a way for me to run the GMXL in WTP space with 3 alternative specific cost parameters? Thanks,Thames From wgreene at stern.nyu.edu Sat Mar 7 00:19:26 2020 From: wgreene at stern.nyu.edu (William Greene) Date: Fri, 6 Mar 2020 08:19:26 -0500 Subject: [Limdep Nlogit List] GMXL (WTP space) in Nlogit In-Reply-To: <499292086.438801.1583454936741@mail.yahoo.com> References: <499292086.438801.1583454936741.ref@mail.yahoo.com> <499292086.438801.1583454936741@mail.yahoo.com> Message-ID: Dear Thamarasi Kularatne. Unfortunately, no, it will not work. NLOGIT's routine is specifically written to expect a single normalized coefficient. The computations are specifically programmed with a single normalization. What you suggest below would require the full set of parameters for each alternative to be normalized separately. For those parameters that are common across alternatives, it's not clear how this could be achieved while keeping the model internally consistent. Regards, Bill Greene On Thu, Mar 5, 2020 at 7:36 PM Thamarasi Kularatne via Limdep < limdep at mailman.sydney.edu.au> wrote: > Hi, > I'm trying to run a generalised mixed logit model (GMXL) in WTP space in > order to account for taste and scale heterogeneity. > As explained in the Nlogit 6 reference guide, we can choose one of the > parameters in the GMXLOGIT model to have a coefficient of one and build > this nonlinearity into the GMXLOGIT model by changing its type to (*type) > in the ; Fcn = (*type),? specification. > In my case, I have 3 alternatives and the cost parameters need to be > alternative specific. Therefore when estimating GMXL in WTP space, I need > to specify 3 fixed parameters. example below: > GMXlogit ;userp > ;lhs=choice,cset,altij > ;choices=oral,inject,infuse,none > ;pds=9 ;halton ;pts=10 > ;fcn=ocost(*n),icost(*n),ivcost(*n),eff(n),mild(n),inj_6m(n),spec(n) > ;par > ;pwt > ;gmx > ;cor > ;gamma=0 > ;tau=0.1 > ;Model: > U(oral)=eff*eff+ oral_wee*oral_wee + oral_m*oral_mon + mild*mild_se + > sev2*sev_2 + ocost*oralcost+ spec*spec+ oself*oral_sel / > U(inject)=inject+eff*eff+ inj_w*inj_week + inj_m*inj_mon + inj_6m*inj_6mon > + inj_y*inj_yr + mild*mild_se + sev2*sev_2+ icost*injcost+ > spec*spec+iadmin*admin_in / > U(infuse)=infuse+ eff*eff+ mild*mild_se + sev2*sev_2+ivcost*ivcost+ > iv_6m*iv_6mon + iv_yr*iv_yr + spec*spec + ivadmin*admin_iv/ > U(none)=None $ > This does not work. Nlogit only takes one parameter at a time with a * in > the fcn specification. Is there a way for me to run the GMXL in WTP space > with 3 alternative specific cost parameters? > Thanks,Thames > _______________________________________________ > 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/77s8Ck8vAZtOnrP2Qt2XbIf?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 Charles.RAUX at laet.msh-lse.fr Wed Mar 25 21:40:46 2020 From: Charles.RAUX at laet.msh-lse.fr (RAUX Charles) Date: Wed, 25 Mar 2020 10:40:46 +0000 Subject: [Limdep Nlogit List] sample selection and multinomial logit In-Reply-To: References: <3BE1FEAD-3100-496F-B0D2-BB6F3015B109@gmail.com> <72D6B3FEC474FA40B4981EDD2D672981F21E6829@CNMB02WVP.core-res.rootcore.local> <72D6B3FEC474FA40B4981EDD2D672981010FAA07E2@CNREXCMBX01P.core-res.rootcore.local> Message-ID: <72D6B3FEC474FA40B4981EDD2D672981010FC2DBC4@CNREXCMBX06P.core-res.rootcore.local> Hello, I am trying to estimate an mlogit (mode choice among 4 modes but with only individual characteristics) with sample selection (probit) with Limdep11/Nlogit 6, following the example in documentation E54.5. Choice is coded from 0 to 3. If I run mlogit without selection then I get expected results (asc and coef for 3 modes). If I run probit/hold and the mlogit/selection, it happens as if choice is treated as binary. I don't get the coefficients for each value of choice (see below). What's wrong? Charles Raux Histogram for CHOICE NOBS = 21994, Too low: 0, Too high: 0 Bin Value of CHOICE Frequency Cumulative Frequency ======================================================================== 0 0 17828 ( .8106) 17828 ( .8106) 1 1 1859 ( .0845) 19687 ( .8951) 2 2 1746 ( .0794) 21433 ( .9745) 3 3 561 ( .0255) 21994 (1.0000) |-> PROBIT ; Lhs = treated ; Rhs = wi ; Hold $ Iterative procedure has converged Normal exit: 5 iterations. Status=0, F= .1234722D+05 ----------------------------------------------------------------------------- Binomial Probit Model Dependent variable TREATED Log likelihood function -12347.22015 Restricted log likelihood -12500.76863 Chi squared [ 13](P= .000) 307.09697 Significance level .00000 McFadden Pseudo R-squared .0122831 Estimation based on N = 21994, K = 14 Inf.Cr.AIC = 24722.4 AIC/N = 1.124 Results retained for SELECTION model. --------+-------------------------------------------------------------------- | Standard Prob. 95% Confidence TREATED| Coefficient Error z |z|>Z* Interval --------+-------------------------------------------------------------------- |Index function for probability...................................... Constant| -.78312*** .08955 -8.75 .0000 -.95863 -.60761 AGE25| .12817*** .04069 3.15 .0016 .04842 .20792 AGE35| .11733*** .03895 3.01 .0026 .04100 .19367 AGE45| .01710 .03832 .45 .6555 -.05802 .09221 AGE55| -.10244** .04274 -2.40 .0165 -.18620 -.01867 TENANT_S| -.24980*** .04804 -5.20 .0000 -.34395 -.15565 OWNER| .20638*** .02572 8.02 .0000 .15598 .25679 DIPL_B| .02215 .03312 .67 .5036 -.04277 .08707 DIPL_C| -.12201*** .03438 -3.55 .0004 -.18938 -.05463 DIPL_D| -.26711*** .03084 -8.66 .0000 -.32755 -.20666 LESS1| .07153 .08387 .85 .3937 -.09285 .23592 MORE1| .08690 .08161 1.06 .2870 -.07305 .24684 IMMIGRAN| -.07866* .04030 -1.95 .0510 -.15766 .00033 NBHHMEMB| .00104 .00857 .12 .9034 -.01575 .01783 --------+-------------------------------------------------------------------- ***, **, * ==> Significance at 1%, 5%, 10% level. Model was estimated on Mar 25, 2020 at 11:27:23 AM ----------------------------------------------------------------------------- |-> mlogit ; lhs = choice ; rhs= x ; selection $ ----------------------------------------------------------------------------- Logit Regression Start Values for CHOICE Dependent variable CHOICE Log likelihood function -2432.51826 Estimation based on N = 21994, K = 13 Inf.Cr.AIC = 4891.0 AIC/N = .222 --------+-------------------------------------------------------------------- | Standard Prob. 95% Confidence CHOICE| Coefficient Error z |z|>Z* Interval --------+-------------------------------------------------------------------- Constant| .07131 .28867 .25 .8049 -.49448 .63710 FEMALE| .44169*** .07420 5.95 .0000 .29627 .58712 AGE25| -.70372*** .15601 -4.51 .0000 -1.00949 -.39796 AGE35| -.41604*** .14006 -2.97 .0030 -.69055 -.14153 AGE45| -.30388** .13683 -2.22 .0264 -.57207 -.03569 AGE55| -.12381 .15168 -.82 .4144 -.42109 .17348 TENANT_S| -.02040 .20471 -.10 .9206 -.42163 .38083 OWNER| -.06119 .10202 -.60 .5486 -.26115 .13876 DIPL_B| -.15659 .11770 -1.33 .1834 -.38729 .07410 DIPL_C| -.20521 .12578 -1.63 .1028 -.45173 .04132 DIPL_D| -.32594*** .11476 -2.84 .0045 -.55087 -.10101 LESS1| -.78624*** .26338 -2.99 .0028 -1.30246 -.27002 MORE1| -1.49821*** .25773 -5.81 .0000 -2.00335 -.99307 --------+-------------------------------------------------------------------- ***, **, * ==> Significance at 1%, 5%, 10% level. Model was estimated on Mar 25, 2020 at 11:27:34 AM ----------------------------------------------------------------------------- Line search at iteration 33 does not improve the function Exiting optimization ----------------------------------------------------------------------------- Selectivity Corrected Logit Model Dependent variable CHOICE Log likelihood function -117023.96957 Estimation based on N = 21994, K = 29 Inf.Cr.AIC = 234105.9 AIC/N = 10.644 --------+-------------------------------------------------------------------- | Standard Prob. 95% Confidence CHOICE| Coefficient Error z |z|>Z* Interval --------+-------------------------------------------------------------------- |Coefficients in binary logit model.................................. Constant| .55154*** .18670 2.95 .0031 .18561 .91746 FEMALE| .22248*** .03102 7.17 .0000 .16167 .28329 AGE25| -.48749*** .06552 -7.44 .0000 -.61592 -.35907 AGE35| -.22802*** .06060 -3.76 .0002 -.34680 -.10923 AGE45| -.12163** .05922 -2.05 .0400 -.23769 -.00556 AGE55| .00545 .06721 .08 .9353 -.12627 .13717 TENANT_S| -.11913 .09211 -1.29 .1959 -.29967 .06141 OWNER| -.04290 .04130 -1.04 .2990 -.12386 .03805 DIPL_B| -.02995 .04838 -.62 .5360 -.12478 .06489 DIPL_C| -.16904*** .05171 -3.27 .0011 -.27040 -.06769 DIPL_D| -.54675*** .04745 -11.52 .0000 -.63975 -.45374 LESS1| -.33793* .17950 -1.88 .0597 -.68974 .01388 MORE1| -.95063*** .17724 -5.36 .0000 -1.29802 -.60324 |Coefficients in Probit = Alpha/sqr(1-rho^2)......................... Constant| -.78287*** .09006 -8.69 .0000 -.95938 -.60637 AGE25| .12822*** .04067 3.15 .0016 .04851 .20794 AGE35| .11746*** .03892 3.02 .0025 .04118 .19374 AGE45| .01714 .03836 .45 .6550 -.05804 .09231 AGE55| -.10247** .04284 -2.39 .0168 -.18644 -.01850 TENANT_S| -.24968*** .04781 -5.22 .0000 -.34340 -.15597 OWNER| .20652*** .02551 8.09 .0000 .15652 .25653 DIPL_B| .02209 .03322 .66 .5061 -.04302 .08719 DIPL_C| -.12208*** .03450 -3.54 .0004 -.18970 -.05445 DIPL_D| -.26721*** .03093 -8.64 .0000 -.32783 -.20659 LESS1| .07133 .08340 .86 .3924 -.09213 .23479 MORE1| .08664 .08114 1.07 .2856 -.07239 .24568 IMMIGRAN| -.07886* .04045 -1.95 .0512 -.15814 .00043 NBHHMEMB| .00101 .00863 .12 .9067 -.01591 .01793 |Standard deviation of e(i) in logit model........................... Sigma(e)| .02441 .01526 1.60 .1096 -.00549 .05432 |Correlation of selection u(i) and logit e(i)........................ Rho(u,e)| -.00391 .00925 -.42 .6722 -.02205 .01422 --------+-------------------------------------------------------------------- ***, **, * ==> Significance at 1%, 5%, 10% level. Model was estimated on Mar 25, 2020 at 11:35:25 AM ----------------------------------------------------------------------------- From mpuri at ufl.edu Sun Mar 29 10:19:30 2020 From: mpuri at ufl.edu (Puri,Mahi) Date: Sat, 28 Mar 2020 23:19:30 +0000 Subject: [Limdep Nlogit List] Error message in running Stated Choice Model Message-ID: Hello I am using NLOGIT (version 6) and trying to run Mixed (Random Parameter) Logit Model for stated choice experiment data. However, the model is giving an error and we are unable to proceed. Please advice. The code, description of data and error message are provided below: 1. The data is in the form of panel data (3 repetitions) where each respondent is given 3 choices (alt 1, alt 2, none). So, 600 respondents*3 choices*3 repetitions = 5400 rows of data 2. The attributes (land, year, payment) vary over choices. 3. Covariates/characteristics (padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources) vary across respondents. 4. "land" and "year" are random parameters |-> NLOGIT; Lhs = choiced ; Choices = alt1, alt2, none ; model: U(alt1) = b_land * land + b_year * year + b_payment * payment/ U(alt2) = b_land * land + b_year * year + b_payment * payment/ U(none) = asc + b_land * land + b_year * year + b_payment * payment ; RPL = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources ; Pts = 500; Halton; Pds = 3 ; Fcn = b_land(n), b_year(n)$ ----------------------------------------------------------------------------- Start values obtained using MNL model Dependent variable Choice Log likelihood function -1588.38429 Estimation based on N = 1773, K = 4 Inf.Cr.AIC = 3184.8 AIC/N = 1.796 --------------------------------------- Log likelihood R-sqrd R2Adj Constants only -1913.0514 .1697 .1602 Note: R-sqrd = 1 - logL/Logl(constants) Warning: Model does not contain a full set of ASCs. R-sqrd is problematic. Use model setup with ;RHS=one to get LogL0. --------------------------------------- Response data are given as ind. choices Number of obs.= 1800, skipped 27 obs --------+-------------------------------------------------------------------- | Standard Prob. 95% Confidence CHOICED| Coefficient Error z |z|>Z* Interval --------+-------------------------------------------------------------------- B_LAND| -.04070*** .00181 -22.51 .0000 -.04425 -.03716 B_YEAR| -.02464** .01144 -2.15 .0313 -.04707 -.00221 B_PAYMEN| .01460*** .00225 6.50 .0000 .01020 .01900 ASC| -1.59020*** .16806 -9.46 .0000 -1.91960 -1.26080 --------+-------------------------------------------------------------------- ***, **, * ==> Significance at 1%, 5%, 10% level. Model was estimated on Mar 28, 2020 at 06:25:54 PM ----------------------------------------------------------------------------- Error 805: Initial iterations cannot improve function.Status=3 Function value was .1588384288D+04 at entry ----------- .3124865903D+05 at exit ----------- Error 1025: Failed to fit model. See earlier diagnostic. ---- Mahi Puri PhD Candidate and Graduate Assistant Wildlife Ecology and Conservation University of Florida From mpuri at ufl.edu Sun Mar 29 10:19:30 2020 From: mpuri at ufl.edu (Puri,Mahi) Date: Sat, 28 Mar 2020 23:19:30 +0000 Subject: [Limdep Nlogit List] Error message in running Stated Choice Model Message-ID: Hello I am using NLOGIT (version 6) and trying to run Mixed (Random Parameter) Logit Model for stated choice experiment data. However, the model is giving an error and we are unable to proceed. Please advice. The code, description of data and error message are provided below: 1. The data is in the form of panel data (3 repetitions) where each respondent is given 3 choices (alt 1, alt 2, none). So, 600 respondents*3 choices*3 repetitions = 5400 rows of data 2. The attributes (land, year, payment) vary over choices. 3. Covariates/characteristics (padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources) vary across respondents. 4. "land" and "year" are random parameters |-> NLOGIT; Lhs = choiced ; Choices = alt1, alt2, none ; model: U(alt1) = b_land * land + b_year * year + b_payment * payment/ U(alt2) = b_land * land + b_year * year + b_payment * payment/ U(none) = asc + b_land * land + b_year * year + b_payment * payment ; RPL = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources ; Pts = 500; Halton; Pds = 3 ; Fcn = b_land(n), b_year(n)$ ----------------------------------------------------------------------------- Start values obtained using MNL model Dependent variable Choice Log likelihood function -1588.38429 Estimation based on N = 1773, K = 4 Inf.Cr.AIC = 3184.8 AIC/N = 1.796 --------------------------------------- Log likelihood R-sqrd R2Adj Constants only -1913.0514 .1697 .1602 Note: R-sqrd = 1 - logL/Logl(constants) Warning: Model does not contain a full set of ASCs. R-sqrd is problematic. Use model setup with ;RHS=one to get LogL0. --------------------------------------- Response data are given as ind. choices Number of obs.= 1800, skipped 27 obs --------+-------------------------------------------------------------------- | Standard Prob. 95% Confidence CHOICED| Coefficient Error z |z|>Z* Interval --------+-------------------------------------------------------------------- B_LAND| -.04070*** .00181 -22.51 .0000 -.04425 -.03716 B_YEAR| -.02464** .01144 -2.15 .0313 -.04707 -.00221 B_PAYMEN| .01460*** .00225 6.50 .0000 .01020 .01900 ASC| -1.59020*** .16806 -9.46 .0000 -1.91960 -1.26080 --------+-------------------------------------------------------------------- ***, **, * ==> Significance at 1%, 5%, 10% level. Model was estimated on Mar 28, 2020 at 06:25:54 PM ----------------------------------------------------------------------------- Error 805: Initial iterations cannot improve function.Status=3 Function value was .1588384288D+04 at entry ----------- .3124865903D+05 at exit ----------- Error 1025: Failed to fit model. See earlier diagnostic. ---- Mahi Puri PhD Candidate and Graduate Assistant Wildlife Ecology and Conservation University of Florida From david.hensher at sydney.edu.au Sun Mar 29 10:40:02 2020 From: david.hensher at sydney.edu.au (David Hensher) Date: Sun, 29 Mar 2020 10:40:02 +1100 Subject: [Limdep Nlogit List] Error message in running Stated Choice Model In-Reply-To: References: Message-ID: <5E7FE052.4080008@sydney.edu.au> I suggest you just rune rpl as ;rpl? without the ' = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources' to see of there is an issue here with such a large number of interacting effect David Henehr On 29/03/2020 10:19 AM, Puri,Mahi wrote: > Hello > > I am using NLOGIT (version 6) and trying to run Mixed (Random Parameter) Logit Model for stated choice experiment data. However, the model is giving an error and we are unable to proceed. Please advice. > > The code, description of data and error message are provided below: > > 1. > The data is in the form of panel data (3 repetitions) where each respondent is given 3 choices (alt 1, alt 2, none). So, 600 respondents*3 choices*3 repetitions = 5400 rows of data > 2. > The attributes (land, year, payment) vary over choices. > 3. > Covariates/characteristics (padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources) vary across respondents. > 4. > "land" and "year" are random parameters > > |-> NLOGIT; Lhs = choiced > > ; Choices = alt1, alt2, none > > ; model: > > U(alt1) = b_land * land + b_year * year + b_payment * payment/ > > U(alt2) = b_land * land + b_year * year + b_payment * payment/ > > U(none) = asc + b_land * land + b_year * year + b_payment * payment > > ; RPL = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources > > ; Pts = 500; Halton; Pds = 3 > > ; Fcn = b_land(n), b_year(n)$ > > > ----------------------------------------------------------------------------- > > Start values obtained using MNL model > > Dependent variable Choice > > Log likelihood function -1588.38429 > > Estimation based on N = 1773, K = 4 > > Inf.Cr.AIC = 3184.8 AIC/N = 1.796 > > --------------------------------------- > > Log likelihood R-sqrd R2Adj > > Constants only -1913.0514 .1697 .1602 > > Note: R-sqrd = 1 - logL/Logl(constants) > > Warning: Model does not contain a full > > set of ASCs. R-sqrd is problematic. Use > > model setup with ;RHS=one to get LogL0. > > --------------------------------------- > > Response data are given as ind. choices > > Number of obs.= 1800, skipped 27 obs > > --------+-------------------------------------------------------------------- > > | Standard Prob. 95% Confidence > > CHOICED| Coefficient Error z |z|>Z* Interval > > --------+-------------------------------------------------------------------- > > B_LAND| -.04070*** .00181 -22.51 .0000 -.04425 -.03716 > > B_YEAR| -.02464** .01144 -2.15 .0313 -.04707 -.00221 > > B_PAYMEN| .01460*** .00225 6.50 .0000 .01020 .01900 > > ASC| -1.59020*** .16806 -9.46 .0000 -1.91960 -1.26080 > > --------+-------------------------------------------------------------------- > > ***, **, * ==> Significance at 1%, 5%, 10% level. > > Model was estimated on Mar 28, 2020 at 06:25:54 PM > > ----------------------------------------------------------------------------- > > > > Error 805: Initial iterations cannot improve function.Status=3 > > Function value was .1588384288D+04 at entry ----------- > > .3124865903D+05 at exit ----------- > > Error 1025: Failed to fit model. See earlier diagnostic. > > > ---- > Mahi Puri > > PhD Candidate and Graduate Assistant > Wildlife Ecology and Conservation > University of Florida > > _______________________________________________ > 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 https://protect-au.mimecast.com/s/ia-QCp81lrtx8Y1OfPorWD?domain=sydney.edu.au |W https://protect-au.mimecast.com/s/V2-7Cq71mwf75qKkiXk77W?domain=sydney.edu.au Celebrating 25 years of ITLS: 1991-2016 https://protect-au.mimecast.com/s/4KTbCr81nytDvgPnS4e0Fr?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/jyUUCvl1rKiy6QpLUA9VXd?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/tbcHCwV1vMfR1BJVt1Ia0a?domain=cambridge.org Nlogit is the most popular software for choice modellers. See https://protect-au.mimecast.com/s/T7W2CxngwOfQAYnRiWkHEi?domain=limdep.com See Master of Transport beginning 2020: * Master of Transport: https://sydney.edu.au/courses/courses/pc/master-of-transport.html * Graduate Certificate in Transport: https://sydney.edu.au/courses/courses/pc/graduate-certificate-in-transport.html * Graduate Diploma in Transport: https://sydney.edu.au/courses/courses/pc/graduate-diploma-in-transport.html 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 david.hensher at sydney.edu.au Sun Mar 29 10:40:02 2020 From: david.hensher at sydney.edu.au (David Hensher) Date: Sun, 29 Mar 2020 10:40:02 +1100 Subject: [Limdep Nlogit List] Error message in running Stated Choice Model In-Reply-To: References: Message-ID: <5E7FE052.4080008@sydney.edu.au> I suggest you just rune rpl as ;rpl? without the ' = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources' to see of there is an issue here with such a large number of interacting effect David Henehr On 29/03/2020 10:19 AM, Puri,Mahi wrote: > Hello > > I am using NLOGIT (version 6) and trying to run Mixed (Random Parameter) Logit Model for stated choice experiment data. However, the model is giving an error and we are unable to proceed. Please advice. > > The code, description of data and error message are provided below: > > 1. > The data is in the form of panel data (3 repetitions) where each respondent is given 3 choices (alt 1, alt 2, none). So, 600 respondents*3 choices*3 repetitions = 5400 rows of data > 2. > The attributes (land, year, payment) vary over choices. > 3. > Covariates/characteristics (padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources) vary across respondents. > 4. > "land" and "year" are random parameters > > |-> NLOGIT; Lhs = choiced > > ; Choices = alt1, alt2, none > > ; model: > > U(alt1) = b_land * land + b_year * year + b_payment * payment/ > > U(alt2) = b_land * land + b_year * year + b_payment * payment/ > > U(none) = asc + b_land * land + b_year * year + b_payment * payment > > ; RPL = padist, fcov, herbcon, inputs, benefits, respage, respedu, hhmem, #caste, history, landsize, aginc, crops, otherinc, sources > > ; Pts = 500; Halton; Pds = 3 > > ; Fcn = b_land(n), b_year(n)$ > > > ----------------------------------------------------------------------------- > > Start values obtained using MNL model > > Dependent variable Choice > > Log likelihood function -1588.38429 > > Estimation based on N = 1773, K = 4 > > Inf.Cr.AIC = 3184.8 AIC/N = 1.796 > > --------------------------------------- > > Log likelihood R-sqrd R2Adj > > Constants only -1913.0514 .1697 .1602 > > Note: R-sqrd = 1 - logL/Logl(constants) > > Warning: Model does not contain a full > > set of ASCs. R-sqrd is problematic. Use > > model setup with ;RHS=one to get LogL0. > > --------------------------------------- > > Response data are given as ind. choices > > Number of obs.= 1800, skipped 27 obs > > --------+-------------------------------------------------------------------- > > | Standard Prob. 95% Confidence > > CHOICED| Coefficient Error z |z|>Z* Interval > > --------+-------------------------------------------------------------------- > > B_LAND| -.04070*** .00181 -22.51 .0000 -.04425 -.03716 > > B_YEAR| -.02464** .01144 -2.15 .0313 -.04707 -.00221 > > B_PAYMEN| .01460*** .00225 6.50 .0000 .01020 .01900 > > ASC| -1.59020*** .16806 -9.46 .0000 -1.91960 -1.26080 > > --------+-------------------------------------------------------------------- > > ***, **, * ==> Significance at 1%, 5%, 10% level. > > Model was estimated on Mar 28, 2020 at 06:25:54 PM > > ----------------------------------------------------------------------------- > > > > Error 805: Initial iterations cannot improve function.Status=3 > > Function value was .1588384288D+04 at entry ----------- > > .3124865903D+05 at exit ----------- > > Error 1025: Failed to fit model. See earlier diagnostic. > > > ---- > Mahi Puri > > PhD Candidate and Graduate Assistant > Wildlife Ecology and Conservation > University of Florida > > _______________________________________________ > 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 https://protect-au.mimecast.com/s/imJTC81V0PTwRomoCn4eYw?domain=sydney.edu.au Celebrating 25 years of ITLS: 1991-2016 https://protect-au.mimecast.com/s/53LKC91WPRTYBGJGCErBAK?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/zSzXC0YKPvir31n1S2qVU2?domain=thredbo-conference-series.org https://www.linkedin.com/company/28450714 Second edition of Applied Choice Analysis now available at www.cambridge.org/9781107465923 Nlogit is the most popular software for choice modellers. See www.limdep.com See Master of Transport beginning 2020: * Master of Transport: https://sydney.edu.au/courses/courses/pc/master-of-transport.html * Graduate Certificate in Transport: https://sydney.edu.au/courses/courses/pc/graduate-certificate-in-transport.html * Graduate Diploma in Transport: https://sydney.edu.au/courses/courses/pc/graduate-diploma-in-transport.html 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.