Hello statalist,
I have a problem interpreting my meoprobit outcomes, can anyone help me to do it. The interactions are not good. Does anyone know how to improve this model? Thank you. Lourdes.

MODEL1: NULL MODEL

. meoprobit satisfaction_ordered Country:

Fitting fixed-effects model:

Iteration 0: log likelihood = -32960.327
Iteration 1: log likelihood = -32960.327

Refining starting values:

Grid node 0: log likelihood = -32567.327

Fitting full model:

Iteration 0: log likelihood = -32567.327 (not concave)
Iteration 1: log likelihood = -32561.023 (not concave)
Iteration 2: log likelihood = -32554.723 (not concave)
Iteration 3: log likelihood = -32548.521 (not concave)
Iteration 4: log likelihood = -32542.56 (not concave)
Iteration 5: log likelihood = -32540.081
Iteration 6: log likelihood = -32537.608
Iteration 7: log likelihood = -32533.409
Iteration 8: log likelihood = -32533.399
Iteration 9: log likelihood = -32533.399

Mixed-effects oprobit regression Number of obs = 32,885
Group variable: Country Number of groups = 26

Obs per group:
min = 972
avg = 1,264.8
max = 3,357

Integration method: mvaghermite Integration pts. = 7

chi2() = .
Log likelihood = -32533.399 Prob > chi2 = .

satisfacti~d Coef. Std. Err. z P>z [95% Conf. Interval]

/cut1 -1.970212 .043203 -45.60 0.000 -2.054888 -1.885536
/cut2 -1.073677 .041564 -25.83 0.000 -1.155141 -.9922129
/cut3 .6853506 .0413694 16.57 0.000 .6042681 .7664331

Country
var(_cons) .0428871 .0122385 .0245145 .0750292

LR test vs. oprobit model: chibar2(01) = 853.86 Prob >= chibar2 = 0.0000

MODEL 2: HOFSTEDE CULTURAL VALUES AND INTERACTIONS

. meoprobit satisfaction_ordered public_sector1 female age seniority superior_worker education_primary education_
> tertiary marital_status child agriculture services construction employees_2_9 employees_250_more person_job_fit
> unlimited_contract future_prospect_1 income trustworthiness teams telework training_general routine job_strain_e
> ffort stress work_hours pdi idv mas uai public_pdi public_idv public_mas public_uai unemployment gdppercapitapp
> p score public_unemployment public_score public_gdp Country:

Fitting fixed-effects model:

Iteration 0: log likelihood = -12222.832
Iteration 1: log likelihood = -10776.306
Iteration 2: log likelihood = -10765.163
Iteration 3: log likelihood = -10765.157
Iteration 4: log likelihood = -10765.157

Refining starting values:

Grid node 0: log likelihood = -10782.834

Fitting full model:

Iteration 0: log likelihood = -10782.834 (not concave)
Iteration 1: log likelihood = -10773.512 (not concave)
Iteration 2: log likelihood = -10764.191 (not concave)
Iteration 3: log likelihood = -10753.363 (not concave)
Iteration 4: log likelihood = -10740.699
Iteration 5: log likelihood = -10738.404
Iteration 6: log likelihood = -10737.742
Iteration 7: log likelihood = -10737.735
Iteration 8: log likelihood = -10737.735

Mixed-effects oprobit regression Number of obs = 12,351
Group variable: Country Number of groups = 26

Obs per group:
min = 206
avg = 475.0
max = 1,130

Integration method: mvaghermite Integration pts. = 7

Wald chi2(40) = 2501.20
Log likelihood = -10737.735 Prob > chi2 = 0.0000

satisfaction_ordered Coef. Std. Err. z P>z [95% Conf. Interval]

public_sector1 -.5146032 .6081288 -0.85 0.397 -1.706514 .6773074
female .000699 .0238504 0.03 0.977 -.0460468 .0474449
age -.0021584 .0012014 -1.80 0.072 -.0045131 .0001963
seniority .002461 .00141 1.75 0.081 -.0003026 .0052246
superior_worker .1019307 .0305997 3.33 0.001 .0419563 .1619051
education_primary .0100046 .0692935 0.14 0.885 -.1258082 .1458174
education_tertiary .0906328 .026668 3.40 0.001 .0383644 .1429012
marital_status .0219079 .0260455 0.84 0.400 -.0291402 .0729561
child .01154 .0220604 0.52 0.601 -.0316976 .0547776
agriculture .0241308 .0790291 0.31 0.760 -.1307634 .1790249
services .0265813 .0297462 0.89 0.372 -.0317202 .0848827
construction -.0294421 .0510182 -0.58 0.564 -.1294358 .0705516
employees_2_9 .0303672 .0315227 0.96 0.335 -.0314162 .0921507
employees_250+ -.0643988 .0246632 -2.61 0.009 -.1127378 -.0160598
person_job_fit .0465068 .0217989 2.13 0.033 .0037816 .0892319
unlimited_contract .0855052 .0371816 2.30 0.021 .0126306 .1583798
future_prospect_1 .71721 .0353359 20.30 0.000 .6479529 .7864671
income .0000663 .0000128 5.18 0.000 .0000412 .0000914
trustworthiness .6131421 .0261401 23.46 0.000 .5619085 .6643757
teams .0837657 .0226385 3.70 0.000 .039395 .1281363
telework .0412644 .0113144 3.65 0.000 .0190886 .0634402
training_general .2096173 .0234206 8.95 0.000 .1637137 .2555209
routine -.0549751 .0256104 -2.15 0.032 -.1051705 -.0047798
job_strain_effort .0635692 .0066427 9.57 0.000 .0505497 .0765887
stress -.2596727 .0103035 -25.20 0.000 -.2798673 -.2394782
work_hours -.0067331 .0012273 -5.49 0.000 -.0091385 -.0043277
pdi -.0074371 .0018362 -4.05 0.000 -.011036 -.0038382
idv -.0026181 .0020658 -1.27 0.205 -.0066669 .0014307
mas .0048094 .0011362 4.23 0.000 .0025826 .0070362
uai -1.60e-06 .0018018 -0.00 0.999 -.003533 .0035298
public_pdi .003006 .0018509 1.62 0.104 -.0006218 .0066337
public_idv .0009634 .0017942 0.54 0.591 -.0025531 .0044799
public_mas -.0018304 .0010919 -1.68 0.094 -.0039705 .0003097
public_uai -.0011042 .0015484 -0.71 0.476 -.0041391 .0019307
unemployment -.00808 .0055305 -1.46 0.144 -.0189196 .0027596
gdppercapita -2.34e-06 2.52e-06 -0.93 0.354 -7.29e-06 2.61e-06
score -.006008 .007906 -0.76 0.447 -.0215034 .0094873
public_unemp .0129683 .0045978 2.82 0.005 .0039567 .0219798
public_score .0031748 .0072322 0.44 0.661 -.0110001 .0173496
public_gdp 3.70e-06 2.29e-06 1.61 0.106 -7.91e-07 8.19e-06

/cut1 -3.182658 .7047142 -4.52 0.000 -4.563872 -1.801443
/cut2 -2.123575 .7043463 -3.01 0.003 -3.504069 -.7430821
/cut3 -.0600805 .7041524 -0.09 0.932 -1.440194 1.320033

Country
var(_cons) .0121157 .004399 .005947 .0246833

LR test vs. oprobit model: chibar2(01) = 54.85 Prob >= chibar2 = 0.0000