SV: [Limdep Nlogit List] order probit marginal effects
Fredrik Carlsson
Fredrik.Carlsson at economics.gu.se
Wed Jul 2 20:37:12 EST 2008
I have exactly the same problem, but I'm running Nlogit. The exe-file is therefore called Nlogit.exe, so is there a similar update for Nlogit?
Fredrik
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/
________________________________________
Från: limdep-bounces at limdep.itls.usyd.edu.au [limdep-bounces at limdep.itls.usyd.edu.au] för William Greene [wgreene at stern.nyu.edu]
Skickat: den 2 juli 2008 04:19
Till: Limdep and Nlogit Mailing List
Ämne: Re: [Limdep Nlogit List] order probit marginal effects
If you cannot replicate the following, download the file
http://www.stern.nyu.edu/~wgreene/limdep9.zip
and replace your current copy of limdep.exe. (Back up
your old one. No reinstall, just replace the .exe file.)
/Bill Greene
--> RESET
Initializing NLOGIT Version 4.0.3 (March 1, 2008).
--> samp;1-1000$
--> crea;x=rnn(0,1);y=rnd(5)-1$
--> orde;lhs=y;rhs=one,x;mar$
Normal exit from iterations. Exit status=0.
+---------------------------------------------+
| Ordered Probability Model |
| Maximum Likelihood Estimates |
| Dependent variable Y |
| Weighting variable None |
| Number of observations 1000 |
| Iterations completed 7 |
| Log likelihood function -1605.182 |
| Number of parameters 5 |
| Info. Criterion: AIC = 3.22036 |
| Finite Sample: AIC = 3.22042 |
| Info. Criterion: BIC = 3.24490 |
| Info. Criterion:HQIC = 3.22969 |
| Restricted log likelihood -1605.191 |
| McFadden Pseudo R-squared .0000057 |
| Chi squared .1825517E-01 |
| Degrees of freedom 1 |
| Prob[ChiSqd > value] = .8925236 |
| Model estimated: Jul 01, 2008, 10:16:57PM |
| Underlying probabilities based on Normal |
+---------------------------------------------+
+--------------------------------------------------------------------+
| TABLE OF CELL FREQUENCIES FOR ORDERED PROBABILITY MODEL |
+--------------------------------------------------------------------+
| Frequency Cumulative < = Cumulative > = |
|Outcome Count Percent Count Percent Count Percent |
|----------- ------- --------- ------- --------- ------- --------- |
|Y=00 197 19.7000 197 19.7000 1000 100.0000 |
|Y=01 200 20.0000 397 39.7000 803 80.3000 |
|Y=02 232 23.2000 629 62.9000 603 60.3000 |
|Y=03 197 19.7000 826 82.6000 371 37.1000 |
|Y=04 174 17.4000 1000 100.0000 174 17.4000 |
+--------------------------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
+--------+Index function for probability |
|Constant| .85234*** .03541933 24.064 .0000 |
|X | .00445 .03293147 .135 .8925 .0170880|
+--------+Threshold parameters for index |
|Mu(1) | .59131*** .03242623 18.236 .0000 |
|Mu(2) | 1.18166*** .03742509 31.574 .0000 |
|Mu(3) | 1.79090*** .04704372 38.069 .0000 |
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
========================================================================
||Summary of Marginal Effects for Ordered Probability Model (probit) ||
||Effects computed at means. Effectsfor binary variables are ||
||computed as differences of probabilities, other variables at means. ||
========================================================================
|| Continuous Variable ONE Continuous Variable X
|| ============================== ==============================
Outcome Effect dPy<=nn/dX dPy>=nn/dX Effect dPy<=nn/dX dPy>=nn/dX
======= ============================== ==============================
Y = 00 .00000 .00000 .00000 -.00123 -.00123 .00000
Y = 01 .00000 .00000 .00000 -.00048 -.00172 .00123
Y = 02 .00000 .00000 .00000 .00003 -.00168 .00172
Y = 03 .00000 .00000 .00000 .00054 -.00114 .00168
Y = 04 .00000 .00000 .00000 .00114 .00000 .00114
========================================================================
+---------------------------------------------------------------------------+
| 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| 197| 0| 0| 197| 0| 0|
| 1| 200| 0| 0| 200| 0| 0|
| 2| 232| 0| 0| 232| 0| 0|
| 3| 197| 0| 0| 197| 0| 0|
| 4| 174| 0| 0| 174| 0| 0|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
|Col Sum| 1000| 0| 0| 1000| 0| 0| 0| 0| 0| 0| 0|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
NOW WITH FULL OUTPUT....
--> orde;lhs=y;rhs=one,x;mar;full$
Normal exit from iterations. Exit status=0.
+---------------------------------------------+
| Ordered Probability Model |
| Maximum Likelihood Estimates |
| Dependent variable Y |
| Weighting variable None |
| Number of observations 1000 |
| Iterations completed 7 |
| Log likelihood function -1605.182 |
| Number of parameters 5 |
| Info. Criterion: AIC = 3.22036 |
| Finite Sample: AIC = 3.22042 |
| Info. Criterion: BIC = 3.24490 |
| Info. Criterion:HQIC = 3.22969 |
| Restricted log likelihood -1605.191 |
| McFadden Pseudo R-squared .0000057 |
| Chi squared .1825517E-01 |
| Degrees of freedom 1 |
| Prob[ChiSqd > value] = .8925236 |
| Model estimated: Jul 01, 2008, 10:17:22PM |
| Underlying probabilities based on Normal |
+---------------------------------------------+
+--------------------------------------------------------------------+
| TABLE OF CELL FREQUENCIES FOR ORDERED PROBABILITY MODEL |
+--------------------------------------------------------------------+
| Frequency Cumulative < = Cumulative > = |
|Outcome Count Percent Count Percent Count Percent |
|----------- ------- --------- ------- --------- ------- --------- |
|Y=00 197 19.7000 197 19.7000 1000 100.0000 |
|Y=01 200 20.0000 397 39.7000 803 80.3000 |
|Y=02 232 23.2000 629 62.9000 603 60.3000 |
|Y=03 197 19.7000 826 82.6000 371 37.1000 |
|Y=04 174 17.4000 1000 100.0000 174 17.4000 |
+--------------------------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
+--------+Index function for probability |
|Constant| .85234*** .03541933 24.064 .0000 |
|X | .00445 .03293147 .135 .8925 .0170880|
+--------+Threshold parameters for index |
|Mu(1) | .59131*** .03242623 18.236 .0000 |
|Mu(2) | 1.18166*** .03742509 31.574 .0000 |
|Mu(3) | 1.79090*** .04704372 38.069 .0000 |
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
========================================================================
||Summary of Marginal Effects for Ordered Probability Model (probit) ||
||Effects computed at means. Effectsfor binary variables are ||
||computed as differences of probabilities, other variables at means. ||
========================================================================
|| Continuous Variable ONE Continuous Variable X
|| ============================== ==============================
Outcome Effect dPy<=nn/dX dPy>=nn/dX Effect dPy<=nn/dX dPy>=nn/dX
======= ============================== ==============================
Y = 00 .00000 .00000 .00000 -.00123 -.00123 .00000
Y = 01 .00000 .00000 .00000 -.00048 -.00172 .00123
Y = 02 .00000 .00000 .00000 .00003 -.00168 .00172
Y = 03 .00000 .00000 .00000 .00054 -.00114 .00168
Y = 04 .00000 .00000 .00000 .00114 .00000 .00114
========================================================================
+----------------------------------------------------+
| Marginal effects for ordered probability model |
| These are the effects on Prob[Y=00] at means. |
| M.E.s for dummy variables are Pr[y|x=1]-Pr[y|x=0] |
| Names for dummy variables are marked by *. |
+----------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
|Constant| .000*** ......(Fixed Parameter)....... |
|X | -.00123 .00913588 -.135 .8925 .0170880|
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
|Fixed Parameter... indicates a parameter that is constrained to equal|
|a fixed value (e.g., 0) or a serious estimation problem. If you did |
|not impose a restriction on the parameter, check for previous errors.|
+---------------------------------------------------------------------+
+----------------------------------------------------+
| Marginal effects for ordered probability model |
| These are the effects on Prob[Y=01] at means. |
| M.E.s for dummy variables are Pr[y|x=1]-Pr[y|x=0] |
| Names for dummy variables are marked by *. |
+----------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
|Constant| .000 ......(Fixed Parameter)....... |
|X | -.00048 .00356178 -.135 .8925 .0170880|
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
|Fixed Parameter... indicates a parameter that is constrained to equal|
|a fixed value (e.g., 0) or a serious estimation problem. If you did |
|not impose a restriction on the parameter, check for previous errors.|
+---------------------------------------------------------------------+
+----------------------------------------------------+
| Marginal effects for ordered probability model |
| These are the effects on Prob[Y=02] at means. |
| M.E.s for dummy variables are Pr[y|x=1]-Pr[y|x=0] |
| Names for dummy variables are marked by *. |
+----------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
|Constant| .000 ......(Fixed Parameter)....... |
|X | .34163D-04 .00025549 .134 .8936 .0170880|
+--------+------------------------------------------------------------+
| Note: nnnnn.D-xx or D+xx => multiply by 10 to -xx or +xx. |
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
|Fixed Parameter... indicates a parameter that is constrained to equal|
|a fixed value (e.g., 0) or a serious estimation problem. If you did |
|not impose a restriction on the parameter, check for previous errors.|
+---------------------------------------------------------------------+
+----------------------------------------------------+
| Marginal effects for ordered probability model |
| These are the effects on Prob[Y=03] at means. |
| M.E.s for dummy variables are Pr[y|x=1]-Pr[y|x=0] |
| Names for dummy variables are marked by *. |
+----------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
|Constant| .000 ......(Fixed Parameter)....... |
|X | .00054 .00398773 .135 .8926 .0170880|
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
|Fixed Parameter... indicates a parameter that is constrained to equal|
|a fixed value (e.g., 0) or a serious estimation problem. If you did |
|not impose a restriction on the parameter, check for previous errors.|
+---------------------------------------------------------------------+
+----------------------------------------------------+
| Marginal effects for ordered probability model |
| These are the effects on Prob[Y=04] at means. |
| M.E.s for dummy variables are Pr[y|x=1]-Pr[y|x=0] |
| Names for dummy variables are marked by *. |
+----------------------------------------------------+
+--------+--------------+----------------+--------+--------+----------+
|Variable| Coefficient | Standard Error |b/St.Er.|P[|Z|>z]| Mean of X|
+--------+--------------+----------------+--------+--------+----------+
|Constant| .000 ......(Fixed Parameter)....... |
|X | .00114 .00845751 .135 .8925 .0170880|
+--------+------------------------------------------------------------+
| Note: ***, **, * = Significance at 1%, 5%, 10% level. |
+---------------------------------------------------------------------+
|Fixed Parameter... indicates a parameter that is constrained to equal|
|a fixed value (e.g., 0) or a serious estimation problem. If you did |
|not impose a restriction on the parameter, check for previous errors.|
+---------------------------------------------------------------------+
+---------------------------------------------------------------------------+
| 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| 197| 0| 0| 197| 0| 0|
| 1| 200| 0| 0| 200| 0| 0|
| 2| 232| 0| 0| 232| 0| 0|
| 3| 197| 0| 0| 197| 0| 0|
| 4| 174| 0| 0| 174| 0| 0|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
|Col Sum| 1000| 0| 0| 1000| 0| 0| 0| 0| 0| 0| 0|
+-------+-------+-----+-----+-----+-----+-----+-----+-----+-----+-----+-----+
----- Original Message -----
From: "Blane Lewis" <mblewis at indo.net.id>
To: "Limdep and Nlogit Mailing List" <limdep at limdep.itls.usyd.edu.au>
Sent: Tuesday, July 1, 2008 8:50:40 PM (GMT-0500) America/New_York
Subject: Re: [Limdep Nlogit List] order probit marginal effects
Bill,
Thanks for the quick response. It doesn't work, however. (Nor do any of the obvious alternatives: ;output=1,2,3 or full etc).
Any other suggestions?
Thanks,
Blane
----- Original Message -----
From: William Greene
To: Limdep and Nlogit Mailing List
Sent: Tuesday, July 01, 2008 6:16 PM
Subject: Re: [Limdep Nlogit List] order probit marginal effects
Blane: Try adding ;FULL OUTPUT to the ORDERED command.
/B. Greene
----- Original Message -----
From: "Blane Lewis" <mblewis at indo.net.id>
To: limdep at limdep.itls.usyd.edu.au
Sent: Tuesday, July 1, 2008 6:02:05 AM (GMT-0500) America/Bogota
Subject: [Limdep Nlogit List] order probit marginal effects
Hello Limdepers:
I'm running an ordered probit model (using Limdep 9.0) and want to get the program to produce detailed information on the marginal effects (as per the example in the manual on page E22-8).
When I include the command "margins" I get only the summary output, i.e. just the marginal effects of the independent variable for y= 0, 1, 2, and 3 but no standard errors, t stats, etc.
What command should I use to get the full output?
Thanks,
Blane
_______________________________________________
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
_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au
_______________________________________________
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
_______________________________________________
Limdep site list
Limdep at limdep.itls.usyd.edu.au
http://limdep.itls.usyd.edu.au
More information about the Limdep
mailing list