[Limdep Nlogit List] Marginal effects in ordered probit
William Greene
wgreene at stern.nyu.edu
Wed Jun 18 23:02:51 EST 2008
Fredrik: Try adding ;ALL to the command.
/Bill Greene
----- Original Message -----
From: "Fredrik Carlsson" <Fredrik.Carlsson at economics.gu.se>
To: "Limdep and Nlogit Mailing List" <limdep at limdep.itls.usyd.edu.au>
Sent: Wednesday, June 18, 2008 7:49:39 AM (GMT-0500) America/Bogota
Subject: [Limdep Nlogit List] Marginal effects in ordered probit
With the new version of limdep I seem to not get the details for the marginal effects, only the summary (and hence not the p-values). Anyone knows what I'm doing wrong?
So this command: ordered;lhs=oq38a; rhs=x;Marginal Effects$
Gives this output only
Normal exit from iterations. Exit status=0.
+---------------------------------------------+
| Ordered Probability Model |
| Maximum Likelihood Estimates |
| Model estimated: Jun 18, 2008 at 02:48:42PM.|
| Dependent variable OQ38A |
| Weighting variable None |
| Number of observations 885 |
| Iterations completed 26 |
| Log likelihood function -710.5927 |
| Number of parameters 21 |
| Info. Criterion: AIC = 1.65332 |
| Finite Sample: AIC = 1.65453 |
| Info. Criterion: BIC = 1.76687 |
| Info. Criterion:HQIC = 1.69673 |
| Restricted log likelihood -760.3851 |
| McFadden Pseudo R-squared .0654831 |
| Chi squared 99.58478 |
| Degrees of freedom 18 |
| Prob[ChiSqd > value] = .0000000 |
| Underlying probabilities based on Normal |
+---------------------------------------------+
+---------------------------------------------+
| Ordered Probability Model |
| Cell frequencies for outcomes |
| Y Count Freq Y Count Freq Y Count Freq |
| 0 17 .019 1 43 .048 2 249 .281 |
| 3 576 .650 |
+---------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
---------+Index function for probability
Constant| 1.92104164 .19543673 9.829 .0000
AGEG2 | .02077632 .12822090 .162 .8713 .29265537
AGEG3 | .20022378 .12108471 1.654 .0982 .30960452
AGEG4 | .40176336 .15057344 2.668 .0076 .18531073
WOMEN | .21001712 .08650375 2.428 .0152 .54463277
BARN | -.04539165 .10763824 -.422 .6732 .37514124
GYMN | .06094490 .12768786 .477 .6332 .38870056
UNIV | .26692592 .13264362 2.012 .0442 .44519774
EQINCOME| -.02077273 .03598516 -.577 .5638 1.43041997
RELIG | .08244915 .11743920 .702 .4826 .17288136
LANDET | .00153036 .10120428 .015 .9879 .32203390
STORSTAD| -.15628777 .10604985 -1.474 .1406 .26214689
SAP | .16509654 .13773242 1.199 .2307 .24745763
CENTER | -.07271455 .14447756 -.503 .6148 .19322034
M | .44425278 .15550443 2.857 .0043 .18531073
OTHERP | .62760474 .28400864 2.210 .0271 .03389831
BLANK | -.89043024 .18427980 -4.832 .0000 .06327684
NOOPIN | -.32045733 .15616310 -2.052 .0402 .11638418
NOTVOTE | .01728707 .54336030 .032 .9746 .00677966
---------+Threshold parameters for index
Mu(1) | .66302773 .06087258 10.892 .0000
Mu(2) | 1.87502803 .07035728 26.650 .0000
+-------------------------------------------------------------------------+
| Summary of Marginal Effects for Ordered Probability Model (probit) |
+-------------------------------------------------------------------------+
Variable| Y=00 Y=01 Y=02 Y=03 Y=04 Y=05 Y=06 Y=07 |
--------------------------------------------------------------------------+
*AGEG2 -.0006 -.0016 -.0054 .0076
*AGEG3 -.0054 -.0148 -.0520 .0722
*AGEG4 -.0091 -.0262 -.1029 .1382
*WOMEN -.0063 -.0166 -.0543 .0772
*BARN .0014 .0036 .0118 -.0167
*GYMN -.0018 -.0047 -.0158 .0223
*UNIV -.0077 -.0204 -.0690 .0971
EQINCOME .0006 .0016 .0054 -.0076
*RELIG -.0023 -.0062 -.0214 .0299
*LANDET .0000 -.0001 -.0004 .0006
*STORSTA .0050 .0128 .0403 -.0581
*SAP -.0044 -.0121 -.0429 .0594
*CENTER .0022 .0058 .0188 -.0269
*M -.0098 -.0285 -.1133 .1516
*OTHERP -.0099 -.0319 -.1522 .1941
*BLANK .0639 .1050 .1749 -.3438
*NOOPIN .0126 .0293 .0804 -.1222
*NOTVOTE -.0005 -.0013 -.0045 .0063
+---------------------------------------------------------------------------+
| Cross tabulation of predictions. Row is actual, column is predicted. |
| Model = Probit . Prediction is number of the most probable cell. |
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
| Actual|Row Sum| 0 | 1 | 2 | 3 | 4 | 5 | 6 | 7 | 8 | 9 |
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
| 0| 17| 0| 0| 10| 7|
| 1| 43| 0| 0| 10| 33|
| 2| 249| 0| 0| 30| 219|
| 3| 576| 0| 0| 24| 552|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
|Col Sum| 885| 0| 0| 74| 811| 0| 0| 0| 0| 0| 0|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
Fredrik Carlsson
Professor
Department of Economics, University of Gothenburg
Box 640, SE-405 40 Gothenburg, Sweden
Tel: +46 31 7864174
Fax: +46 31 7861043
Mobile: +46 0709 267 097
Home page:
http://www.handels.gu.se/econ/fredrik.carlsson/
_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au
--
Professor William Greene
Department of Economics
Stern School of Business
New York University
44 West 4th St., Rm. 7-78
New York, NY 10012
http://www.stern.nyu.edu/~wgreene
212.998.0876
More information about the Limdep
mailing list