问题
I have a categorical variable n_produttore: A-B-C-D-E-F
and the output of multinomial logit (mlogit).
How do I create the confusion matrix?
mlogit n_produttore UVAtevola NUTILIZZODIVOLTE EXPOSTFIORITURA DIMENSIONE DOSI
Iteration 0: log likelihood = -898.93386
Iteration 1: log likelihood = -868.27679
Iteration 2: log likelihood = -864.38774
Iteration 3: log likelihood = -864.28614
Iteration 4: log likelihood = -864.26279
Iteration 5: log likelihood = -864.25805
Iteration 6: log likelihood = -864.25724
Iteration 7: log likelihood = -864.25705
Iteration 8: log likelihood = -864.25701
Iteration 9: log likelihood = -864.257
Multinomial logistic regression Number of obs = 929
LR chi2(25) = 69.35
Prob > chi2 = 0.0000
Log likelihood = -864.257 Pseudo R2 = 0.0386
----------------------------------------------------------------------------------
n_produttore | Coef. Std. Err. z P>|z| [95% Conf. Interval]
-----------------+----------------------------------------------------------------
ALTRO | (base outcome)
-----------------+----------------------------------------------------------------
A |
UVAtevola | -.1579633 .3240817 -0.49 0.626 -.7931517 .4772251
NUTILIZZODIVOLTE | -.2306291 .0957196 -2.41 0.016 -.418236 -.0430221
EXPOSTFIORITURA | -.1879822 .2277447 -0.83 0.409 -.6343536 .2583893
DIMENSIONE | -.0621528 .022512 -2.76 0.006 -.1062755 -.01803
DOSI | .0749472 .0469926 1.59 0.111 -.0171565 .167051
_cons | -.9914935 .2967274 -3.34 0.001 -1.573068 -.4099185
-----------------+----------------------------------------------------------------
B |
UVAtevola | -1.125263 .5444485 -2.07 0.039 -2.192362 -.0581633
NUTILIZZODIVOLTE | -.0667538 .0966905 -0.69 0.490 -.2562637 .1227562
EXPOSTFIORITURA | -.769514 .2891922 -2.66 0.008 -1.33632 -.2027077
DIMENSIONE | -.0293445 .022586 -1.30 0.194 -.0736122 .0149232
DOSI | -.0451004 .1109894 -0.41 0.684 -.2626356 .1724349
_cons | -1.361353 .3900545 -3.49 0.000 -2.125846 -.5968602
-----------------+----------------------------------------------------------------
C |
UVAtevola | -1.232848 1.075072 -1.15 0.251 -3.33995 .8742545
NUTILIZZODIVOLTE | -.1639186 .2256885 -0.73 0.468 -.6062599 .2784227
EXPOSTFIORITURA | -.154228 .5543342 -0.28 0.781 -1.240703 .9322469
DIMENSIONE | -.0993675 .0590232 -1.68 0.092 -.2150508 .0163159
DOSI | .0816812 .1273864 0.64 0.521 -.1679916 .3313541
_cons | -2.727106 .7170044 -3.80 0.000 -4.132409 -1.321803
-----------------+----------------------------------------------------------------
D |
UVAtevola | -14.83818 1290.627 -0.01 0.991 -2544.421 2514.745
NUTILIZZODIVOLTE | -.3792106 .4314916 -0.88 0.379 -1.224919 .4664973
EXPOSTFIORITURA | -.4976473 .8798813 -0.57 0.572 -2.222183 1.226888
DIMENSIONE | -.0976071 .0905061 -1.08 0.281 -.2749958 .0797817
DOSI | -.2036094 .4729157 -0.43 0.667 -1.130507 .7232883
_cons | -2.242187 1.425189 -1.57 0.116 -5.035506 .5511316
-----------------+----------------------------------------------------------------
E |
UVAtevola | .7193533 .2948825 2.44 0.015 .1413942 1.297312
NUTILIZZODIVOLTE | -.1058946 .0921645 -1.15 0.251 -.2865337 .0747446
EXPOSTFIORITURA | -.4057074 .2529228 -1.60 0.109 -.901427 .0900122
DIMENSIONE | -.0641196 .025192 -2.55 0.011 -.113495 -.0147442
DOSI | .0965401 .0441483 2.19 0.029 .010011 .1830692
_cons | -1.615742 .3101875 -5.21 0.000 -2.223698 -1.007786
----------------------------------------------------------------------------------
predict prob*
egen pred_max = rowmax(prob*)
(23 missing values generated)
.
.
.
. g pred_choice = .
(952 missing values generated)
.
. forvalues i = 1/6 {
2.
. replace pred_choice = `i' if (pred_max == prob`i')
3.
. }
(951 real changes made)
(23 real changes made)
(23 real changes made)
(23 real changes made)
(23 real changes made)
(24 real changes made)
.
.
.
. local produttore_lab: value label n_produttore
.
. label values pred_choice `produttore_lab'
.
. tab pred_choice n_produttore
pred_choic | n_produttore
e | ALTRO A B C D E | Total
-----------+------------------------------------------------------------------+----------
ALTRO | 666 95 67 14 6 80 | 928
E | 21 1 0 0 0 2 | 24
-----------+------------------------------------------------------------------+----------
Total | 687 96 67 14 6 82 | 952
where: n_produttore = ALTRO A B C D E
UVAtevola = dummy 0 or 1
NUTILIZZODIVOLTE = 1...15
EXPOSTFIORITURA = dummy 0 or 1
DIMENSIONE = 1....50 kg
DOSI: 1....20
回答1:
Your code seems to be taken from an answer by Tzygmund McFarlane in Statalist.org. I reproduce the complete, working example below:
webuse sysdsn1, clear
mlogit insure age male nonwhite i.site
predict prob*
egen pred_max = rowmax(prob*)
g pred_choice = .
forv i=1/3 {
replace pred_choice = `i' if (pred_max == prob`i')
}
local insure_lab: value label insure
label values pred_choice `insure_lab'
tab pred_choice insure
Like I said, it works. So unless you give more information on the problem you have at hand, people may not be able to help you. There may be an issue with your model specification, with your data structure, a combination, or something else. Your statement
... but it doesn't work.
gives nothing for people to work with. Good practice is to post exact input/output, including errors. Please read the complete Asking section in https://stackoverflow.com/help.
来源：https://stackoverflow.com/questions/23912352/how-to-create-a-confusion-matrix-after-mlogit