[Limdep Nlogit List] Simulation using estimates from SP data and ASCs from RP data
William Greene
wgreene at stern.nyu.edu
Mon Jul 6 05:22:58 AEST 2020
The same subsample,
|-> sample;all$
|-> reject;sprp=1$
is being used for both estimation and simulation.
It sounds like you want to fit the model with one subset of the
data and do the simulation with a different one. That is OK, just
set the samples accordingly for the two cases.
/B. Greene
On Fri, Jul 3, 2020 at 10:31 PM Thao Thai via Limdep <
limdep at mailman.sydney.edu.au> wrote:
> Hi Nlogit users,
>
> I am simulating some scenarios using the coefficient estimates from a CL
> model on SP data and alternative specific constants (ASCs) calibrated to
> reflect the RP data.
>
> However, the reported market shares in the base case shows the market
> shares observed in SP data. The reported market shares of the simulated
> scenarios are also compared to these SP data market shares, which I think
> is not correct (It should be compared to the market shares from RP data)?
>
> Could you please kindly let me know if my syntax below is correct?
>
> Thank you so much for your help!
> Thao
>
> |-> sample;all$
> |-> reject;sprp=1$
> |-> Nlogit
> ;lhs = cho, cset, alti
> ;choices = H, C, P, I, G, N
> ;crosstabs
> ;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
> $
> +----------------------------------------------------------+
> | Inspecting the data set before estimation. |
> | These errors mark observations which will be skipped. |
> | Row Individual = 1st row then group number of data block |
> +----------------------------------------------------------+
> No bad observations were found in the sample
>
> Iterative procedure has converged
> Normal exit: 5 iterations. Status=0, F= .4001834D+04
>
>
> -----------------------------------------------------------------------------
> Discrete choice (multinomial logit) model
> Dependent variable Choice
> Log likelihood function -4001.83388
> Estimation based on N = 2434, K = 32
> Inf.Cr.AIC = 8067.7 AIC/N = 3.315
> ---------------------------------------
> Log likelihood R-sqrd R2Adj
> ASCs only model must be fit separately
> Use NLOGIT ;...;RHS=ONE$
> Note: R-sqrd = 1 - logL/Logl(constants)
> ---------------------------------------
> Chi-squared[27] = 655.81735
> Prob [ chi squared > value ] = .00000
> Response data are given as ind. choices
> Number of obs.= 2434, skipped 0 obs
>
> --------+--------------------------------------------------------------------
> | Standard Prob. 95% Confidence
> CHO| Coefficient Error z |z|>Z* Interval
>
> --------+--------------------------------------------------------------------
> RL_H1| .07005 .16175 .43 .6650 -.24697 .38707
> RL_H2| .23104* .13433 1.72 .0855 -.03225 .49433
> FL_| .17867*** .05585 3.20 .0014 .06920 .28813
> CR_H1| .27104** .13131 2.06 .0390 .01368 .52840
> CR_2| .05296 .09477 .56 .5763 -.13279 .23871
> LO_H1| -.41466*** .12119 -3.42 .0006 -.65219 -.17713
> SA_| .01231*** .00086 14.30 .0000 .01062 .01399
> COM| -.10806 .15871 -.68 .4959 -.41913 .20300
> RL_C1| .38787** .16751 2.32 .0206 .05956 .71618
> RL_C2| .26364* .15216 1.73 .0832 -.03459 .56187
> CR_C1| .19661 .13691 1.44 .1510 -.07174 .46496
> LO_C1| -.22246* .12854 -1.73 .0835 -.47440 .02949
> LO_C2| -.82061*** .15800 -5.19 .0000 -1.13027 -.51094
> PRI| .40590*** .14002 2.90 .0037 .13146 .68034
> RL_P1| .01672 .12447 .13 .8932 -.22725 .26068
> CR_P1| .33357** .13132 2.54 .0111 .07619 .59095
> LO_P1| -.95156*** .14221 -6.69 .0000 -1.23029 -.67282
> LO_P2| -1.03276*** .14087 -7.33 .0000 -1.30885 -.75667
> IND| -1.11685*** .15286 -7.31 .0000 -1.41645 -.81725
> RL_I1| .64312*** .14665 4.39 .0000 .35570 .93054
> RL_I2| .79032*** .15550 5.08 .0000 .48555 1.09508
> CR_I1| .61024*** .12199 5.00 .0000 .37115 .84933
> LO_I1| -.64615*** .12354 -5.23 .0000 -.88828 -.40402
> GOV| -.07470 .14043 -.53 .5948 -.34993 .20053
> RL_G1| -.33174** .12927 -2.57 .0103 -.58510 -.07838
> CR_G1| .51684*** .12294 4.20 .0000 .27588 .75781
> LO_G1| -.57783*** .12464 -4.64 .0000 -.82212 -.33354
> NON| -.26651* .14521 -1.84 .0665 -.55112 .01810
> RL_N1| -.08143 .13884 -.59 .5576 -.35355 .19070
> CR_N1| .36292*** .13942 2.60 .0092 .08965 .63618
> LO_N1| -.58506*** .15904 -3.68 .0002 -.89677 -.27336
> LO_N2| -.46639*** .16171 -2.88 .0039 -.78333 -.14945
>
> --------+--------------------------------------------------------------------
> ***, **, * ==> Significance at 1%, 5%, 10% level.
> Model was estimated on Jul 04, 2020 at 00:17:29 PM
>
> -----------------------------------------------------------------------------
>
> |-> sample;all$
> |-> reject;sprp=1$
> |-> Nlogit
> ;lhs = cho, cset, alti
> ;choices = H, C, P, I, G, N/0.23,0.53,0.04,0.04,0.09,0.07
> ;checkdata
> ;show
> 'Alg=BFGS
> ;calibrate
> ; simulation
> ; scenario: RL_C1(c)=1/RL_C2(c)=0
> ;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$
> +----------------------------------------------------------+
> | Inspecting the data set before estimation. |
> | These errors mark observations which will be skipped. |
> | Row Individual = 1st row then group number of data block |
> +----------------------------------------------------------+
> No bad observations were found in the sample
>
>
> Sample proportions are marginal, not conditional.
> Choices marked with * are excluded for the IIA test.
> +----------------+------+
> |Choice (prop.)| Count|
> +----------------+------+
> |H .18447| 449|
> |C .17707| 431|
> |P .19721| 480|
> |I .17502| 426|
> |G .14749| 359|
> |N .11873| 289|
> +----------------+------+
>
>
> +---------------------------------------------+
> | Discrete Choice (One Level) Model |
> | Model Simulation Using Previous Estimates |
> | Number of observations 2434 |
> +---------------------------------------------+
>
> +------------------------------------------------------+
> |Simulations of Probability Model |
> |Model: Discrete Choice (One Level) Model |
> |Simulated choice set may be a subset of the choices. |
> |Number of individuals is the probability times the |
> |number of observations in the simulated sample. |
> |Column totals may be affected by rounding error. |
> |The model used was simulated with 2434 observations.|
> +------------------------------------------------------+
> -------------------------------------------------------------------------
> Specification of scenario 1 is:
> Attribute Alternatives affected Change type Value
> --------- ------------------------------- ------------------- ---------
> RL_C1 C Fix base at new vlu 1.000
> RL_C2 C Fix base at new vlu .000
> -------------------------------------------------------------------------
> The simulator located 2434 observations for this scenario.
> Simulated Probabilities (shares) for this scenario:
> +----------+--------------+--------------+------------------+
> |Choice | Base | Scenario | Scenario - Base |
> | |%Share Number |%Share Number |ChgShare ChgNumber|
> +----------+--------------+--------------+------------------+
> |H | 18.447 449 | 17.950 437 | -.497% -12 |
> |C | 17.707 431 | 19.889 484 | 2.182% 53 |
> |P | 19.721 480 | 19.142 466 | -.579% -14 |
> |I | 17.502 426 | 17.095 416 | -.407% -10 |
> |G | 14.749 359 | 14.335 349 | -.415% -10 |
> |N | 11.873 289 | 11.589 282 | -.284% -7 |
> |Total |100.000 2434 |100.000 2434 | .000% 0 |
> +----------+--------------+--------------+------------------+
> _______________________________________________
> 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/fnofCWLVXkU9jgOjF62sjW?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
More information about the Limdep
mailing list