[Limdep Nlogit List] HEV model results
Twan Huybers
T.Huybers at adfa.edu.au
Wed Jun 10 15:04:51 EST 2009
Dear All,
I have two queries regarding the estimation results of an HEV model.
1) I have run an HEV model which contains eight generic alternatives
with various attributes. The dataset is a stacked one with the first
four alternatives coming from one sample and the second four from
another sample. The IVs are set to be equal for the first four, and
equal (and normalised) for the second four. The estimated scale
parameters themselves are not significant but the implied standard
deviations of the random components are significant - see output below.
In assessing the departure from MNL, which ones should prevail, the
scale parameters or the implied standard deviations? And how come these
two sets of parameters have different significances in the first place?
2) My second query concerns the calculation of HEV choice probabilities.
My understanding has always been that these are not in a closed form
and, therefore, have to be obtained using simulated maximum likelihood.
However, I have now come across a ''parameterised heteroskedastic MNL
model' whose choice probabilities seem, simply, to be equivalent to the
MNL ones after duly multiplying by each alternative's estimated scale
parameter. Does this mean that I can use my HEV scale parameters to
"adjust" each alternatives utility value and, hence, probability?
Thanks for any comments/suggestions.
Regards,
Twan Huybers
--> sample;all$
--> INCLUDE;
new;
origin=10$
--> reject; timecomp<10$
--> nlogit; choices = Alt1, Alt2, Alt3, Alt4, Alt5, Alt6, Alt7, Alt8;
lhs=ch1_7,setsize,aposnrnw;
hetero;
ivset: (Alt1, Alt2, Alt3, Alt4)/
(Alt5, Alt6, Alt7, Alt8)=[1.0];
model:
U(Alt1, Alt2, Alt3, Alt4, Alt5, Alt6, Alt7, Alt8)=
barts*aarts+benter*aenter+bevent*aevent+bfood*afood+bnat*anat+brelax*are
l...
+bqantas*aqantas+bhertz*ahertz+b3ns*a3nights+ba3s*aacc3sta+bvalta*avalta
+bbang*abangkok+bhunt*ahunter+bmarg*amargriv+bnz*anz+byarra*ayarra+bper*
a...
+bexp3s*aexp3sta+bvalexp*avalexp
+bdaarts*daarts+bdaenter*daenter+bdaevent*daevent+bdafood*dafood+bdanat*
d...
+bda3ns*da3night+bdac3st*daacc3st+bdavalta*davalta+bdabang*dabangko+bdan
z...
+bdamarg*damargri+bdasyd*dasyd+bdamelb*damelb+bdaperth*daperth+bdaex3st*
d...
matrix$
Normal exit from iterations. Exit status=0.
+---------------------------------------------+
| Heteroskedastic Extreme Value Model |
| Maximum Likelihood Estimates |
| Model estimated: May 07, 2009 at 10:41:17AM.|
| Dependent variable CH1_7 |
| Weighting variable None |
| Number of observations 827 |
| Iterations completed 53 |
| Log likelihood function -946.3179 |
| Number of parameters 45 |
| Info. Criterion: AIC = 2.39738 |
| Finite Sample: AIC = 2.40379 |
| Info. Criterion: BIC = 2.65410 |
| Info. Criterion:HQIC = 2.49585 |
| Restricted log likelihood -1719.698 |
| McFadden Pseudo R-squared .4497186 |
| Chi squared 1546.761 |
| Degrees of freedom 45 |
| Prob[ChiSqd > value] = .0000000 |
| Constants only. Must be computed directly. |
| Use NLOGIT ;...; RHS=ONE $ |
| At start values -1016.6446 .06918 ******* |
| Response data are given as ind. choice. |
+---------------------------------------------+
+---------------------------------------------+
| Heteroskedastic Extreme Value Model |
| Number of obs.= 828, skipped 1 bad obs. |
+---------------------------------------------+
+--------+--------------+----------------+--------+--------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]|
+--------+--------------+----------------+--------+--------+
BARTS | .75775690 .25663342 2.953 .0032
BENTER | 1.68322496 .39743666 4.235 .0000
BEVENT | 1.09515213 .28778638 3.805 .0001
BFOOD | 1.07041633 .30239119 3.540 .0004
BNAT | 1.25174919 .30734785 4.073 .0000
BRELAX | 1.73474738 .38811315 4.470 .0000
BSPORT | .67938776 .26286290 2.585 .0098
BQANTAS | .05063589 .04728376 1.071 .2842
BHERTZ | -.00172411 .05392820 -.032 .9745
B3NS | -.27085886 .07036760 -3.849 .0001
BA3S | -.25100797 .07174301 -3.499 .0005
BVALTA | .00371064 .00079682 4.657 .0000
BBANG | .73551308 .18990806 3.873 .0001
BHUNT | .09777008 .19219050 .509 .6110
BMARG | -.01642736 .20051373 -.082 .9347
BNZ | 1.53256072 .33925164 4.517 .0000
BYARRA | -.14114760 .20716562 -.681 .4957
BPER | -.47829278 .44204797 -1.082 .2793
BSYD | .22714536 .18114961 1.254 .2099
BMEL | .75784680 .22756093 3.330 .0009
BEXP3S | -.17372057 .06039305 -2.876 .0040
BVALEXP | .00221294 .00050827 4.354 .0000
BDAARTS | -.13416933 .25830063 -.519 .6035
BDAENTER| -.30312232 .39756337 -.762 .4458
BDAEVENT| -.14655652 .28686616 -.511 .6094
BDAFOOD | -.20918860 .30287265 -.691 .4898
BDANAT | -.10700940 .30682955 -.349 .7273
BDARELAX| -.21742008 .38866143 -.559 .5759
BDASPORT| -.21865871 .26101272 -.838 .4022
BDAQANT | .03564620 .04721536 .755 .4503
BDAHERTZ| .00883824 .05393695 .164 .8698
BDA3NS | .02743594 .07099010 .386 .6991
BDAC3ST | .04825748 .07248086 .666 .5055
BDAVALTA| .994394D-04 .00079155 .126 .9000
BDABANG | .33380016 .19132340 1.745 .0810
BDANZ | -.13947213 .34058772 -.410 .6822
BDAHUNT | -.15443945 .19269729 -.801 .4229
BDAYARRA| .01932251 .20713870 .093 .9257
BDAMARG | .27177991 .19965398 1.361 .1734
BDASYD | .14824649 .18117262 .818 .4132
BDAMELB | -.03029755 .22738651 -.133 .8940
BDAPERTH| .22789645 .44707154 .510 .6102
BDAEX3ST| .01760473 .06086719 .289 .7724
BDAVALEX| .00074614 .00051487 1.449 .1473
---------+Scale Parameters of Extreme Value Distns Minus 1.0
s_ALT1 | -.04389759 .33172993 -.132 .8947
s_ALT2 | -.04389759 .33172993 -.132 .8947
s_ALT3 | -.04389759 .33172993 -.132 .8947
s_ALT4 | -.04389759 .33172993 -.132 .8947
s_ALT5 | .000000 ......(Fixed Parameter).......
s_ALT6 | .000000 ......(Fixed Parameter).......
s_ALT7 | .000000 ......(Fixed Parameter).......
s_ALT8 | .000000 ......(Fixed Parameter).......
---------+Std.Dev=pi/(theta*sqr(6)) for H.E.V. distribution.
s_ALT1 | 1.34143559 .46542538 2.882 .0039
s_ALT2 | 1.34143559 .46542538 2.882 .0039
s_ALT3 | 1.34143559 .46542538 2.882 .0039
s_ALT4 | 1.34143559 .46542538 2.882 .0039
s_ALT5 | 1.28254980 ......(Fixed Parameter).......
s_ALT6 | 1.28254980 ......(Fixed Parameter).......
s_ALT7 | 1.28254980 ......(Fixed Parameter).......
s_ALT8 | 1.28254980 ......(Fixed Parameter).......
More information about the Limdep
mailing list