[Limdep Nlogit List] Please help
William Greene
wgreene at stern.nyu.edu
Fri Oct 28 10:16:06 AEDT 2022
I do not see any shaded error messages. the estimator worked OK. But,
I suspect your specification that all the RP's are correlated is not helping
here. I would drop the ;COR from your command.
/B. Greene
On Thu, Oct 27, 2022 at 6:24 AM Harold Mayaba via Limdep <
limdep at mailman.sydney.edu.au> wrote:
>
> Dear Professor Greene and Nlogit users,I sent a text seeking for some help
> two weeks ago but i did not receive any response. While waiting for someone
> to respond, i have been teaching myself on how to use Nlogit. Below are the
> results i got from Nlogit. Please i need some help to check if i'm in the
> right track. I'm getting errors which are highlighted in yellow. What do i
> have to do from this point?
> Regards
> HaroldI
>
> Error 1084: Expectedequation specs. of form U(...) after MODEL:
> |-> Removing data with errors
>
> reject;alti=-999$
>
> Error 1:Unrecognized command. (Missing ; ?)
>
> |-> CALC
>
> ; ran(12345) $
>
> |-> RPLOGIT
>
> ; Lhs=CHOICE
>
> ; CHOICES = alti1
>
> , alti2
>
> , alti3
>
> ; Model:
>
> U(alti1)
>
> =aalti1 +CAGED*CAGED + ACDOORS*ACDOORS + NPRS*NPRS + CERT1*CERT1 +
> CERT2*CERT2 +MMORT*MMORT + HMORT*HMORT + PRICE*PRICE/
>
> U (alti2)
>
> =aalti2 +CAGED*CAGED + ACDOORS*ACDOORS + NPRS*NPRS + CERT1*CERT1 +
> CERT2*CERT2 +MMORT*MMORT + HMORT*HMORT + PRICE*PRICE/
>
> U (alti3)
>
> = None
>
> ; Fcn = CAGED(n ),ACDOORS(n ),NPRS(n),CERT1(n),CERT2(n)
>
> ,MMORT(n),HMORT(n)
>
> ; Correlated
>
> ; Halton
>
> ; Pds=10
>
> ; Pts =100
>
> ; maxit = 200
>
> ; WTP=caged/price,acdoors/price
>
> ,nprs/price
>
> ,cert1/price,cert2/price,mmort/price,hmort/price
>
> ; Par $
>
>
>
> +------------------------------------------------------+
>
> |WARNING: Badobservations were found in the sample. |
>
> |Found 19 badobservations among 9550 individuals. |
>
> |You can use ;CheckData to get a list of these points. |
>
> +------------------------------------------------------+
>
>
>
> Hessian is not positive definite at start values.
>
> Error 803: Hessianis not positive definite at start values.
>
> B0 is too far from solution for Newton method.
>
> Switching to BFGS as a better solution method.
>
> Line search at iteration 17 does not improve the function
>
> Exiting optimization
>
>
>
>
> -----------------------------------------------------------------------------
>
> Start values obtained using MNL model
>
> Dependent variable Choice
>
> Log likelihood function -8498.75280
>
> Estimation based on N = 9531, K = 11
>
> Inf.Cr.AIC = 17019.5 AIC/N = 1.786
>
> ---------------------------------------
>
> Loglikelihood R-sqrd R2Adj
>
> Constants only ********** .1756 .1739
>
> Note: R-sqrd = 1 - logL/Logl(constants)
>
> Warning: Model doesnot 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.= 9550,skipped 19 obs
>
>
> --------+--------------------------------------------------------------------
>
> | Standard Prob. 95% Confidence
>
> CHOICE| Coefficient Error z |z|>Z* Interval
>
>
> --------+--------------------------------------------------------------------
>
> CAGED| -.88357*** .06461 -13.68 .0000 -1.01020 -.75694
>
> ACDOORS| 1.41491 .....(Fixed Parameter).....
>
> NPRS| .09041*** .01401 6.46 .0000 .06296 .11786
>
> CERT1| .08503*** .00895 9.50 .0000 .06749 .10257
>
> CERT2| .13907 .....(Fixed Parameter).....
>
> MMORT| -.27848*** .01713 -16.26 .0000 -.31205 -.24491
>
> HMORT| -.71218 .....(Fixed Parameter).....
>
> AALTI1| .10722 .....(Fixed Parameter).....
>
> PRICE| -.11620 .....(Fixed Parameter).....
>
> AALTI2| .26486 .....(Fixed Parameter).....
>
> NONE| -.37207 .....(Fixed Parameter).....
>
>
> --------+--------------------------------------------------------------------
>
> ***, **, * ==> Significance at 1%, 5%, 10% level.
>
> Fixed parameter ... is constrained to equal the value or
>
> had a nonpositive st.error because of an earlier problem.
>
> Model was estimated on Oct 27, 2022 at 09:18:18 PM
>
>
> -----------------------------------------------------------------------------
>
>
>
> Iterative procedure has converged
>
> Normal exit: 58iterations. Status=0, F= .6426683D+04
>
>
>
>
> -----------------------------------------------------------------------------
>
> Random Parameters Multinom. Logit Model
>
> Dependent variable CHOICE
>
> Log likelihood function -6426.68312
>
> Restricted log likelihood -10470.87372
>
> Chi squared [ 39](P= .000) 8088.38121
>
> Significance level .00000
>
> McFadden Pseudo R-squared .3862324
>
> Estimation based on N = 9531, K = 39
>
> Inf.Cr.AIC = 12931.4 AIC/N = 1.357
>
> ---------------------------------------
>
> Loglikelihood R-sqrd R2Adj
>
> No coefficients ********** .3862 .3850
>
> Constants only ********** .3766 .3753
>
> At start values -8498.7528 .2438 .2423
>
> Note: R-sqrd = 1 - logL/Logl(constants)
>
> Warning: Model doesnot 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
>
> Replications for simulated probs. = 100
>
> Used Halton sequences in simulations.
>
> RPL model with panel has 955 groups
>
> Fixed number of obsrvs./group= 10
>
> Number of obs.= 9550,skipped 19 obs
>
>
> --------+--------------------------------------------------------------------
>
> | Standard Prob. 95% Confidence
>
> CHOICE| Coefficient Error z |z|>Z* Interval
>
>
> --------+--------------------------------------------------------------------
>
> |Randomparameters in utility
> functions..............................
>
> CAGED| -3.89672*** .21748 -17.92 .0000 -4.32296 -3.47047
>
> ACDOORS| 2.50498*** .10415 24.05 .0000 2.30084 2.70912
>
> NPRS| -1.32085*** .18871 -7.00 .0000 -1.69071 -.95098
>
> CERT1| .45899*** .14691 3.12 .0018 .17106 .74693
>
> CERT2| .52836*** .14091 3.75 .0002 .25218 .80454
>
> MMORT| -.71662*** .07380 -9.71 .0000 -.86126 -.57197
>
> HMORT| -1.64829*** .07890 -20.89 .0000 -1.80293 -1.49365
>
> |Nonrandomparameters in utility
> functions...........................
>
> AALTI1| .73535 .4843D+07 .00 1.0000*********** ***********
>
> PRICE| -.22131*** .00963 -22.97 .0000 -.24019 -.20243
>
> AALTI2| .98003 .4843D+07 .00 1.0000*********** ***********
>
> NONE| -1.71538 .4843D+07 .00 1.0000 *********** ***********
>
> |Diagonalvalues in Cholesky matrix,
> L...............................
>
> NsCAGED| 3.37667*** .20165 16.75 .0000 2.98145 3.77190
>
> NsACDOOR| .79580*** .11635 6.84 .0000 .56776 1.02383
>
> NsNPRS| .90651*** .10404 8.71 .0000 .70259 1.11043
>
> NsCERT1| .03803 .15239 .25 .8029 -.26065 .33672
>
> NsCERT2| .24861** .12323 2.02 .0436 .00709 .49013
>
> NsMMORT| .15100 .12500 1.21 .2271 -.09401 .39600
>
> NsHMORT| .13264 .14131 .94 .3479 -.14433 .40960
>
> |Belowdiagonal values in L matrix. V =
> L*Lt.........................
>
> ACDO:CAG| 2.16585*** .11052 19.60 .0000 1.94924 2.38247
>
> NPRS:CAG| -1.75565*** .16547 -10.61 .0000 -2.07996 -1.43133
>
> NPRS:ACD| -.29059** .12683 -2.29 .0219 -.53916 -.04202
>
> CERT:CAG| .39222*** .14720 2.66 .0077 .10371 .68073
>
> CERT:ACD| .25427* .15154 1.68 .0934 -.04274 .55129
>
> CERT:NPR| .74246*** .11386 6.52 .0000 .51929 .96562
>
> CER0:CAG| .38415*** .13671 2.81 .0050 .11621 .65210
>
> CER0:ACD| .02701 .13599 .20 .8426 -.23952 .29353
>
> CER0:NPR| .83787*** .10014 8.37 .0000 .64159 1.03414
>
> CERT:CER| -.22277 .21091 -1.06 .2909 -.63614 .19061
>
> MMOR:CAG| -.50671*** .08597 -5.89 .0000 -.67521 -.33820
>
> MMOR:ACD| -.43917*** .10308 -4.26 .0000 -.64120 -.23714
>
> MMOR:NPR| .09697 .08708 1.11 .2655 -.07370 .26764
>
> MMOR:CER| -.16355 .12911 -1.27 .2052 -.41660 .08950
>
> MMO0:CER| .45088*** .13869 3.25 .0011 .17906 .72271
>
> HMOR:CAG| -1.04303*** .08460 -12.33 .0000 -1.20885 -.87721
>
> HMOR:ACD| -.32097** .16270 -1.97 .0485 -.63985 -.00209
>
> HMOR:NPR| .10747 .10105 1.06 .2875 -.09057 .30552
>
> HMOR:CER| -.16938 .28375 -.60 .5506 -.72552 .38676
>
> HMO0:CER| .64380*** .17109 3.76 .0002 .30846 .97913
>
> HMOR:MMO| -.15210 .16218 -.94 .3483 -.46997 .16577
>
> |Standarddeviations of parameter
> distributions......................
>
> sdCAGED| 3.37667*** .20165 16.75 .0000 2.98145 3.77190
>
> sdACDOOR| 2.30743*** .11427 20.19 .0000 2.08346 2.53139
>
> sdNPRS| 1.99712*** .15613 12.79 .0000 1.69111 2.30314
>
> sdCERT1| .87817*** .13411 6.55 .0000 .61531 1.14102
>
> sdCERT2| .98069*** .12101 8.10 .0000 .74351 1.21787
>
> sdMMORT| .84372*** .12968 6.51 .0000 .58956 1.09788
>
> sdHMORT| 1.29860*** .15640 8.30 .0000 .99206 1.60515
>
> |Covariancesof Random
> Parameters....................................
>
> ACDO:CAG| 7.31338*** .52819 13.85 .0000 6.27815 8.34860
>
> NPRS:CAG| -5.92824*** .56722 -10.45 .0000 -7.03997 -4.81651
>
> NPRS:ACD| -4.03372*** .48360 -8.34 .0000 -4.98155 -3.08589
>
> CERT:CAG| 1.32440*** .49298 2.69 .0072 .35818 2.29063
>
> CERT:ACD| 1.05184*** .35871 2.93 .0034 .34879 1.75490
>
> CERT:NPR| -.08944 .33827 -.26 .7915 -.75243 .57354
>
> CER0:CAG| 1.29716*** .45683 2.84 .0045 .40179 2.19254
>
> CER0:ACD| .85351*** .33054 2.58 .0098 .20566 1.50136
>
> CER0:NPR| .07725 .30183 .26 .7980 -.51432 .66882
>
> CERT:CER| .77115*** .20248 3.81 .0001 .37429 1.16800
>
> MMOR:CAG| -1.71098*** .32097 -5.33 .0000 -2.34007 -1.08189
>
> MMOR:ACD| -1.44694*** .23567 -6.14 .0000 -1.90885 -.98503
>
> MMOR:NPR| 1.10512*** .18359 6.02 .0000 .74529 1.46494
>
> MMOR:CER| -.24463* .12907 -1.90 .0580 -.49760 .00833
>
> MMO0:CER| .02326 .14025 .17 .8683 -.25162 .29814
>
> HMOR:CAG| -3.52197*** .35507 -9.92 .0000 -4.21789 -2.82605
>
> HMOR:ACD| -2.51448*** .31284 -8.04 .0000 -3.12764 -1.90132
>
> HMOR:NPR| 2.02189*** .23524 8.60 .0000 1.56083 2.48294
>
> HMOR:CER| -.41736** .19544 -2.14 .0327 -.80042 -.03430
>
> HMO0:CER| -.12152 .21660 -.56 .5748 -.54604 .30300
>
> HMOR:MMO| .97490*** .19125 5.10 .0000 .60007 1.34974
>
>
> --------+--------------------------------------------------------------------
>
> nnnnn.D-xx or D+xx => multiply by 10 to -xx or +xx.
>
> ***, **, * ==> Significance at 1%, 5%, 10% level.
>
> Model was estimated on Oct 27, 2022 at 09:27:18 PM
>
>
> -----------------------------------------------------------------------------
>
>
>
>
>
>
>
> --------+--------------------------------------------------------------
>
> Cor.Mat.| CAGED ACDOORS NPRS CERT1 CERT2 MMORT HMORT
>
> --------+--------------------------------------------------------------
>
> CAGED| 1.00000 .93865 -.87909 .44664 .39172 -.60056 -.80319
>
> ACDOORS| .93865 1.00000 -.87533 .51909 .37718 -.74323 -.83916
>
> NPRS| -.87909 -.87533 1.00000 -.05100 .03944 .65585 .77961
>
> CERT1| .44664 .51909 -.05100 1.00000 .89542 -.33017 -.36598
>
> CERT2| .39172 .37718 .03944 .89542 1.00000 .02811 -.09542
>
> MMORT| -.60056 -.74323 .65585 -.33017 .02811 1.00000 .88979
>
> HMORT| -.80319 -.83916 .77961 -.36598 -.09542 .88979 1.00000
>
>
>
> Saved Individual Estimates of WTP in matrix WTP_I [ 955x5]
>
> Alternative Attribute Income/Cost
>
> Chosen CAGED PRICE
>
> Chosen ACDOORS PRICE
>
> Chosen NPRS PRICE
>
> Chosen CERT1 PRICE
>
> Chosen CERT2 PRICE
>
> (Saved absolute values. Check signs of coefficients.)
>
> |-> ;RPL$
>
> Error 1:Unrecognized command. (Missing ; ?)
>
> _______________________________________________
> Limdep site list
> Limdep at mailman.sydney.edu.au
> https://protect-au.mimecast.com/s/6swgClx1Njio0gprNUGx89Y?domain=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/BL87CmO5glu5BEDxNiOlrEc?domain=people.stern.nyu.edu
Email: wgreene at stern.nyu.edu
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