Announcement

Collapse
No announcement yet.
X
Collapse
  • Page of 1
  • Filter
  • Time
  • Show
Clear All
new posts
  • #1

    Controls at region and country level

    Dear Statalist,

    I am using the ESWB database. Here is an example of my data and my variables of interest:


    Code:
    * Example generated by -dataex-. For more info, type help dataex
clear
input str26 country_01 double year byte region double idstd float(fin11 lcar1) byte(k7 b8) float(exporter ownership location) long sector double size byte k9
"Argentina2017"      2017 4 622836 1 4.1431346 1 1 0 0 1 1 3 1
"Argentina2017"      2017 4 622402 0  2.995732 1 1 0 0 1 1 2 2
"Armenia2020"        2020 1 708684 0  2.833213 1 . 0 0 1 2 2 1
"Armenia2020"        2020 1 709091 .  2.772589 0 0 0 0 1 2 1 .
"Armenia2020"        2020 1 709039 . 2.1972246 0 0 0 0 0 1 1 .
"Bangladesh2013"     2013 6 532106 .  3.135494 0 1 0 0 1 2 3 .
"Bangladesh2013"     2013 6 531680 .  2.564949 0 0 0 0 1 1 2 1
"Bangladesh2013"     2013 6 531475 1  3.367296 1 0 0 0 1 2 1 1
"Bangladesh2013"     2013 6 531456 1   3.73767 1 0 0 0 1 1 2 1
"Bangladesh2013"     2013 6 532327 1  3.295837 0 1 0 0 0 1 3 2
"Bangladesh2013"     2013 6 532108 .    3.7612 1 0 0 0 1 2 3 .
"Belarus2018"        2018 1 650533 1  2.397895 0 0 0 0 0 1 1 2
"Belgium2020"        2020 1 712861 . 3.6635616 0 0 1 1 1 2 1 .
"Bulgaria2019"       2019 1 679663 1 3.3322046 1 1 0 0 0 1 1 1
"Chile2010"          2010 4 495884 1 3.4011974 1 0 0 0 1 1 2 1
"Chile2010"          2010 4 496523 1  3.367296 1 1 0 0 0 1 2 2
"China2012"          2012 3 523867 .  2.564949 0 1 0 0 1 2 3 .
"China2012"          2012 3 523997 . 2.6390574 0 0 0 0 1 2 1 .
"China2012"          2012 3 522465 1  2.772589 0 1 0 0 1 1 2 2
"China2012"          2012 3 522703 .  2.397895 1 0 0 0 1 1 2 .
"China2012"          2012 3 522528 .  2.944439 0 1 0 0 1 1 3 .
"China2012"          2012 3 523751 . 2.1972246 0 0 0 0 1 2 1 .
"China2012"          2012 3 523976 .  2.772589 0 0 1 0 1 2 1 .
"China2012"          2012 3 522675 .  2.995732 1 1 1 1 1 1 3 2
"Colombia2017"       2017 4 625879 0  2.564949 0 1 0 1 1 2 1 1
"Colombia2017"       2017 4 626322 0  3.465736 1 1 0 0 1 1 1 1
"Costarica2010"      2010 4 501907 1  3.713572 1 0 0 0 1 2 1 2
"Costarica2010"      2010 4 502095 1 3.0445225 0 0 0 0 1 2 2 1
"Czech Republic2019" 2019 1 678733 . 3.3322046 1 1 0 0 0 1 2 .
"Czech Republic2019" 2019 1 678750 0  3.367296 1 1 0 0 0 1 2 1
"Czech Republic2019" 2019 1 678819 1  3.295837 1 1 0 0 0 1 3 1
"Czech Republic2019" 2019 1 678790 .  3.367296 0 1 0 0 0 1 2 .
"Denmark2020"        2020 1 721422 1 4.5849676 1 1 1 1 0 1 3 1
"Denmark2020"        2020 1 720880 .  2.944439 1 1 1 0 0 1 2 .
"Egypt2020"          2020 5 704812 .   1.94591 0 0 0 0 0 2 1 .
"Egypt2020"          2020 5 706085 . 2.0794415 0 0 0 0 1 2 1 .
"Egypt2020"          2020 5 704282 .  3.135494 0 1 0 0 1 1 3 .
"Egypt2020"          2020 5 706221 .  3.433987 0 0 0 0 1 2 2 .
"Egypt2020"          2020 5 706325 . 1.7917595 0 0 0 0 1 2 1 .
"Egypt2020"          2020 5 703814 .  3.295837 1 0 1 0 1 1 3 .
"Egypt2020"          2020 5 704644 .  2.484907 1 0 0 0 1 1 2 .
"ElSalvador2016"     2016 4 605851 .  3.433987 0 0 0 0 1 2 1 .
"Ethiopia2015"       2015 2 590852 0  .6931472 0 0 0 0 0 1 1 3
"Ethiopia2015"       2015 2 590495 1 2.1972246 1 0 0 0 1 2 2 1
"Finland2020"        2020 1 722038 1 4.7004805 1 1 0 0 0 2 2 1
"Finland2020"        2020 1 722084 .   3.89182 1 1 1 0 0 1 3 .
"Finland2020"        2020 1 722262 1 2.0794415 0 0 1 0 0 1 1 1
"Georgia2019"        2019 1 669347 . 1.3862944 0 . 1 0 0 2 1 .
"Georgia2019"        2019 1 669739 .  2.772589 0 . 1 0 1 2 2 .
"Georgia2019"        2019 1 669267 .  2.833213 0 0 0 0 1 2 1 .
"Georgia2019"        2019 1 669631 .  1.609438 0 0 0 0 1 2 2 .
"Ghana2013"          2013 2 557991 . 2.3025851 1 0 0 1 0 2 1 .
"Greece2018"         2018 1 649544 1 3.0445225 1 1 0 0 0 1 3 1
"Greece2018"         2018 1 649550 1  3.433987 1 . 1 0 0 2 3 1
"Greece2018"         2018 1 649618 1 2.0794415 1 1 0 0 0 1 2 1
"Greece2018"         2018 1 649339 . 2.1972246 0 1 0 0 0 1 1 .
"Hungary2019"        2019 1 680257 .  2.484907 0 0 0 0 0 2 1 .
"Hungary2019"        2019 1 680544 0 2.6390574 1 0 1 0 0 2 1 1
"Hungary2019"        2019 1 680471 .  2.772589 0 . 0 0 0 1 1 .
"India2014"          2014 6 566685 1 1.7917595 0 0 0 0 0 1 2 2
"India2014"          2014 6 571165 .  1.609438 1 0 0 0 1 1 2 .
"India2014"          2014 6 565548 1 1.7917595 1 1 0 0 1 1 3 2
"India2014"          2014 6 563360 . 3.3322046 0 0 0 0 1 2 2 .
"India2014"          2014 6 571206 1  2.833213 1 1 0 1 1 1 3 2
"India2014"          2014 6 570433 .   2.70805 1 1 0 0 0 1 3 .
"India2014"          2014 6 565082 1 2.1972246 0 1 0 0 1 1 1 2
"India2014"          2014 6 570847 1 3.5263605 1 1 1 0 0 1 3 1
"India2014"          2014 6 570171 1 1.3862944 1 0 0 0 1 1 1 2
"India2014"          2014 6 567720 .  3.295837 1 0 0 0 1 1 2 .
"India2014"          2014 6 567048 . 3.2580965 0 1 0 0 1 1 2 .
"India2014"          2014 6 570465 .  2.564949 1 1 0 0 0 1 2 .
"India2014"          2014 6 568138 . 2.3025851 1 0 0 0 0 1 1 .
"India2014"          2014 6 570509 . 3.0910425 1 1 0 0 0 1 2 .
"India2014"          2014 6 566869 1   2.70805 1 0 0 0 0 1 1 2
"India2014"          2014 6 571434 1  2.833213 1 1 0 0 1 1 2 2
"India2014"          2014 6 569114 .  2.833213 1 0 0 0 0 1 2 .
"India2014"          2014 6 570345 .   2.70805 1 1 0 0 0 1 3 .
"India2014"          2014 6 567482 .  2.833213 0 . 0 0 0 1 2 .
"India2014"          2014 6 565961 1  3.912023 1 1 0 0 0 1 2 2
"India2014"          2014 6 566068 . 3.2580965 1 1 0 0 0 1 2 .
"India2014"          2014 6 565400 .  3.583519 0 1 0 0 0 1 2 .
"India2014"          2014 6 571318 1 2.6390574 1 0 0 0 0 1 2 2
"India2014"          2014 6 563270 .  1.609438 1 1 0 0 0 2 3 .
"India2014"          2014 6 568961 .  1.609438 1 0 0 0 0 1 2 .
"Indonesia2015"      2015 3 591671 .  2.772589 0 0 0 0 1 2 1 .
"Indonesia2015"      2015 3 591876 .  2.564949 0 0 0 0 1 2 1 .
"Indonesia2015"      2015 3 591284 1 3.8286414 0 0 0 0 1 1 3 2
"Indonesia2015"      2015 3 592396 .   2.70805 0 0 0 0 1 1 3 .
"Indonesia2015"      2015 3 592454 .  2.944439 0 1 0 0 1 1 2 .
"Indonesia2015"      2015 3 591237 .  2.772589 0 0 0 0 0 1 3 .
"Indonesia2015"      2015 3 591314 1 2.6390574 0 0 0 0 1 1 1 2
"Iraq2011"           2011 5 512422 .  1.609438 0 0 0 0 1 1 1 .
"Iraq2011"           2011 5 512689 .  1.609438 0 0 0 0 . 1 1 .
"Italy2019"          2019 1 659203 .  3.912023 1 1 0 0 1 1 3 .
"Italy2019"          2019 1 659189 .  4.304065 1 1 1 0 0 1 3 .
"Jordan2019"         2019 5 662153 .  3.218876 0 0 0 0 . 2 1 .
"Kazakhstan2019"     2019 1 663347 1  1.609438 0 0 0 0 1 1 2 1
"Kazakhstan2019"     2019 1 664042 . 1.7917595 0 0 0 0 1 1 1 .
"Kazakhstan2019"     2019 1 663650 .         . 0 0 0 . 0 1 2 .
"Kazakhstan2019"     2019 1 664259 .   1.94591 0 0 0 0 0 2 2 .
end
label values region region
label def region 1 "ECA", modify
label def region 2 "AFR", modify
label def region 3 "EAP", modify
label def region 4 "LAC", modify
label def region 5 "MNA", modify
label def region 6 "SAR", modify
label values k7 k7
label def k7 0 "No", modify
label def k7 1 "Yes", modify
label values b8 b8
label def b8 0 "No", modify
label def b8 1 "Yes", modify
label values ownership ownership
label def ownership 0 "Domestic", modify
label def ownership 1 "Foreign", modify
label values sector sector
label def sector 1 "Manufacturing", modify
label def sector 2 "Services", modify
label values size size
label def size 1 "Small(<20)", modify
label def size 2 "Medium(20-99)", modify
label def size 3 "Large(100 And Over)", modify
label values k9 K9
label def K9 1 "Private commercial banks", modify
label def K9 2 "State-owned banks or government agency", modify
label def K9 3 "Non-bank financial institutions", modify
    I am trying to estimate the next equation using logistic regression. The code is like this:

    logit fin11 n_outcome lcar1 k7 b8 exporter ownership location sector i.size i.k9

    In one paper that I am using as a reference [Ranasighe & Restuccia (2018), Table 2, page 253], they include region, country and time controls using dummy variables. That is,

    logit fin11 n_outcome lcar1 k7 b8 exporter ownership location sector i.size i.k9 i.country i.region i.year

    All year dummy variables are omitted and 5 country dummies over 60 too due to a collinearity problem. I found that those countries that stata ommits, are one per region. However, I cannot understand why there is a multicollinearity problem, and why in that paper they ignore that problem.

    Thanks in advanced.
    Tags: None
  • #2
    Ibai:
    the issue is that some regerssors predict the outcome perfectly (i.e., no variation):
    Code:
    . logit fin11  lcar1 k7 b8 exporter ownership location sector i.size i.k9

note: 3.size != 0 predicts success perfectly;
      3.size omitted and 9 obs not used.

note: ownership != 0 predicts failure perfectly;
      ownership omitted and 1 obs not used.

note: 3.k9 != 0 predicts failure perfectly;
      3.k9 omitted and 1 obs not used.

note: k7 != 1 predicts success perfectly;
      k7 omitted and 8 obs not used.

note: exporter != 0 predicts failure perfectly;
      exporter omitted and 1 obs not used.

note: b8 != 1 predicts success perfectly;
      b8 omitted and 8 obs not used.

note: sector != 1 predicts success perfectly;
      sector omitted and 1 obs not used.

Iteration 0:   log likelihood = -5.2925059  
Iteration 1:   log likelihood = -1.0422758  
Iteration 2:   log likelihood =          0  
Iteration 3:   log likelihood =          0  

Logistic regression                                     Number of obs =      8
                                                        LR chi2(-1)   =  10.59
                                                        Prob > chi2   =      .
Log likelihood = 0                                      Pseudo R2     = 1.0000

---------------------------------------------------------------------------------------------------------
                                  fin11 | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
----------------------------------------+----------------------------------------------------------------
                                  lcar1 |  -1333.044          .        .       .            .           .
                                     k7 |          0  (omitted)
                                     b8 |          0  (omitted)
                               exporter |          0  (omitted)
                              ownership |          0  (omitted)
                               location |   -1369.07          .        .       .            .           .
                                 sector |          0  (omitted)
                                        |
                                   size |
                         Medium(20-99)  |   -1648.67          .        .       .            .           .
                   Large(100 And Over)  |          0  (empty)
                                        |
                                     k9 |
State-owned banks or government agency  |   2264.861          .        .       .            .           .
       Non-bank financial institutions  |          0  (empty)
                                        |
                                  _cons |   4723.917          .        .       .            .           .
---------------------------------------------------------------------------------------------------------
Note: 3 failures and 5 successes completely determined.
    I'd email the Authors of the paper you mention and ask how they managed the issue.
    Kind regards,
    Carlo
    (Stata 19.0)

    Comment

    • #3
      Originally posted by Carlo Lazzaro View Post
      Ibai:
      the issue is that some regerssors predict the outcome perfectly (i.e., no variation):
      Code:
      . logit fin11 lcar1 k7 b8 exporter ownership location sector i.size i.k9

note: 3.size != 0 predicts success perfectly;
3.size omitted and 9 obs not used.

note: ownership != 0 predicts failure perfectly;
ownership omitted and 1 obs not used.

note: 3.k9 != 0 predicts failure perfectly;
3.k9 omitted and 1 obs not used.

note: k7 != 1 predicts success perfectly;
k7 omitted and 8 obs not used.

note: exporter != 0 predicts failure perfectly;
exporter omitted and 1 obs not used.

note: b8 != 1 predicts success perfectly;
b8 omitted and 8 obs not used.

note: sector != 1 predicts success perfectly;
sector omitted and 1 obs not used.

Iteration 0: log likelihood = -5.2925059
Iteration 1: log likelihood = -1.0422758
Iteration 2: log likelihood = 0
Iteration 3: log likelihood = 0

Logistic regression Number of obs = 8
LR chi2(-1) = 10.59
Prob > chi2 = .
Log likelihood = 0 Pseudo R2 = 1.0000

---------------------------------------------------------------------------------------------------------
fin11 | Coefficient Std. err. z P>|z| [95% conf. interval]
----------------------------------------+----------------------------------------------------------------
lcar1 | -1333.044 . . . . .
k7 | 0 (omitted)
b8 | 0 (omitted)
exporter | 0 (omitted)
ownership | 0 (omitted)
location | -1369.07 . . . . .
sector | 0 (omitted)
|
size |
Medium(20-99) | -1648.67 . . . . .
Large(100 And Over) | 0 (empty)
|
k9 |
State-owned banks or government agency | 2264.861 . . . . .
Non-bank financial institutions | 0 (empty)
|
_cons | 4723.917 . . . . .
---------------------------------------------------------------------------------------------------------
Note: 3 failures and 5 successes completely determined.
      I'd email the Authors of the paper you mention and ask how they managed the issue.
      Hi Carlo,

      Thank you for your answer. May be the example of my data that I posted is not appropiate, because my sample contains almost 20k observations for 60 different countries. When I use my sample, there is no such problem of non-variation (except for two countries, 128 and 259, where the dependent variable fin11, only takes value 1). Here I post the output of my regressions:

      Code:
      . logit fin11  lcar1 k7 b8 exporter ownership location sector  i.size i.k9 if country!=128 & country!=259

Iteration 0:   log likelihood = -12015.957  
Iteration 1:   log likelihood = -11607.546  
Iteration 2:   log likelihood = -11603.212  
Iteration 3:   log likelihood =  -11603.21  
Iteration 4:   log likelihood =  -11603.21  

Logistic regression                                     Number of obs = 19,284
                                                        LR chi2(12)   = 825.49
                                                        Prob > chi2   = 0.0000
Log likelihood = -11603.21                              Pseudo R2     = 0.0343

---------------------------------------------------------------------------------------------------------
                                  fin11 | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
----------------------------------------+----------------------------------------------------------------
                                  lcar1 |  -.1361233   .0234092    -5.81   0.000    -.1820045   -.0902422
                                     k7 |  -.4868381   .0345086   -14.11   0.000    -.5544737   -.4192024
                                     b8 |   .0978016   .0373998     2.62   0.009     .0244994    .1711038
                               exporter |   .1358803   .0419049     3.24   0.001     .0537483    .2180123
                              ownership |  -.0660429   .0593194    -1.11   0.266    -.1823068    .0502211
                               location |  -.1526852   .0323137    -4.73   0.000     -.216019   -.0893514
                                 sector |  -.0317589   .0348871    -0.91   0.363    -.1001364    .0366186
                                        |
                                   size |
                         Medium(20-99)  |   .3366276   .0384094     8.76   0.000     .2613466    .4119086
                   Large(100 And Over)  |   .4284132   .0457756     9.36   0.000     .3386947    .5181317
                                        |
                                     k9 |
State-owned banks or government agency  |   .6391684   .0392505    16.28   0.000     .5622387     .716098
       Non-bank financial institutions  |  -.1879394   .0882534    -2.13   0.033    -.3609129   -.0149659
                                 Other  |  -1.118749   .1497304    -7.47   0.000    -1.412215   -.8252826
                                        |
                                  _cons |   1.164834   .0928971    12.54   0.000      .982759    1.346909
---------------------------------------------------------------------------------------------------------


logit fin11  lcar1 k7 b8 exporter ownership location sector  i.size i.k9 i.country i.region i.year if country!=128 & country!=259, vce(cluster country)

note: 2.region omitted because of collinearity.
note: 3.region omitted because of collinearity.
note: 4.region omitted because of collinearity.
note: 5.region omitted because of collinearity.
note: 6.region omitted because of collinearity.
note: 2011.year omitted because of collinearity.
note: 2012.year omitted because of collinearity.
note: 2013.year omitted because of collinearity.
note: 2014.year omitted because of collinearity.
note: 2015.year omitted because of collinearity.
note: 2016.year omitted because of collinearity.
note: 2017.year omitted because of collinearity.
note: 2018.year omitted because of collinearity.
note: 2019.year omitted because of collinearity.
note: 2020.year omitted because of collinearity.
Iteration 0:   log pseudolikelihood = -12015.957  
Iteration 1:   log pseudolikelihood = -10517.658  
Iteration 2:   log pseudolikelihood = -10456.646  
Iteration 3:   log pseudolikelihood = -10455.165  
Iteration 4:   log pseudolikelihood = -10455.157  
Iteration 5:   log pseudolikelihood = -10455.157  

Logistic regression                                     Number of obs = 19,284
                                                        Wald chi2(11) =      .
                                                        Prob > chi2   =      .
Log pseudolikelihood = -10455.157                       Pseudo R2     = 0.1299

                                                          (Std. err. adjusted for 60 clusters in country)
---------------------------------------------------------------------------------------------------------
                                        |               Robust
                                  fin11 | Coefficient  std. err.      z    P>|z|     [95% conf. interval]
----------------------------------------+----------------------------------------------------------------
                                  lcar1 |  -.0026255   .0310896    -0.08   0.933    -.0635601    .0583091
                                     k7 |  -.0756322   .0849796    -0.89   0.373    -.2421892    .0909249
                                     b8 |   .1249036   .0599805     2.08   0.037      .007344    .2424633
                               exporter |   .1239388   .0603453     2.05   0.040     .0056641    .2422135
                              ownership |  -.1570133   .0886548    -1.77   0.077    -.3307736     .016747
                               location |   -.073328   .0710741    -1.03   0.302    -.2126306    .0659746
                                 sector |   -.036006   .0722839    -0.50   0.618    -.1776798    .1056678
                                        |
                                   size |
                         Medium(20-99)  |    .236467    .067902     3.48   0.000     .1033816    .3695524
                   Large(100 And Over)  |   .2802615   .0597594     4.69   0.000     .1631353    .3973878
                                        |
                                     k9 |
State-owned banks or government agency  |    .205899   .1349049     1.53   0.127    -.0585098    .4703077
       Non-bank financial institutions  |  -.5018669   .1400135    -3.58   0.000    -.7762883   -.2274456
                                 Other  |  -1.448172   .2553297    -5.67   0.000    -1.948609   -.9477345
                                        |
                                country |
                           Armenia2020  |   .8410564   .0679515    12.38   0.000     .7078739    .9742389
                        Bangladesh2013  |   1.940747   .0560378    34.63   0.000     1.830915    2.050578
                           Belarus2018  |   1.088805   .0677292    16.08   0.000     .9560579    1.221552
                           Belgium2020  |  -.7362627   .0534814   -13.77   0.000    -.8410843   -.6314411
                          Bulgaria2019  |   .9418924   .0674681    13.96   0.000     .8096574    1.074127
                             Chile2010  |  -.2639994   .0227351   -11.61   0.000    -.3085594   -.2194393
                             China2012  |   1.024723   .0985069    10.40   0.000      .831653    1.217793
                          Colombia2017  |  -.3156425   .0340164    -9.28   0.000    -.3823135   -.2489716
                         Costarica2010  |   2.361854   .0622416    37.95   0.000     2.239863    2.483846
                    Czech Republic2019  |   1.085682   .0504358    21.53   0.000     .9868301    1.184535
                               DRC2013  |   .9636231   .0591854    16.28   0.000     .8476219    1.079624
                           Denmark2020  |   .8046452   .0573559    14.03   0.000     .6922297    .9170608
                             Egypt2020  |   2.189421   .0855738    25.59   0.000       2.0217    2.357143
                        ElSalvador2016  |    1.44403   .0393105    36.73   0.000     1.366983    1.521077
                          Ethiopia2015  |   1.999711   .0552656    36.18   0.000     1.891392    2.108029
                           Finland2020  |   1.285555   .0540564    23.78   0.000     1.179606    1.391504
                           Georgia2019  |   1.458506   .0769581    18.95   0.000     1.307671    1.609341
                             Ghana2013  |   1.342579   .0453909    29.58   0.000     1.253615    1.431544
                            Greece2018  |    1.32009   .0691377    19.09   0.000     1.184583    1.455598
                           Hungary2019  |   .5087644   .0556327     9.15   0.000     .3997263    .6178025
                             India2014  |   1.276626   .1067755    11.96   0.000      1.06735    1.485902
                         Indonesia2015  |   1.920738   .0813155    23.62   0.000     1.761362    2.080113
                           Ireland2020  |  -.2752492   .0561551    -4.90   0.000    -.3853112   -.1651872
                             Italy2019  |   .1866117   .0570452     3.27   0.001     .0748051    .2984183
                            Jordan2019  |   2.379368   .0486427    48.92   0.000      2.28403    2.474706
                        Kazakhstan2019  |   1.341468   .0695795    19.28   0.000     1.205095    1.477841
                             Kenya2018  |    1.06159   .0379502    27.97   0.000     .9872084    1.135971
                           Lebanon2019  |   1.598772   .0448688    35.63   0.000     1.510831    1.686713
                            Malawi2014  |   3.072267    .043724    70.27   0.000      2.98657    3.157965
                          Malaysia2015  |  -.2524353   .0440109    -5.74   0.000    -.3386951   -.1661754
                            Mexico2010  |   .0801382   .0472885     1.69   0.090    -.0125456     .172822
                           Morocco2019  |   .2515013   .0476869     5.27   0.000     .1580367     .344966
                        Mozambique2018  |   2.857745   .0711215    40.18   0.000     2.718349     2.99714
                           Myanmar2016  |   3.483534    .078615    44.31   0.000     3.329452    3.637617
                           Namibia2014  |   .0825441   .0507886     1.63   0.104    -.0169997    .1820879
                       Netherlands2020  |   .9782813   .0586364    16.68   0.000     .8633561    1.093207
                           Nigeria2014  |   2.219756   .1162971    19.09   0.000     1.991818    2.447694
                          Pakistan2013  |   .6093749   .0310348    19.64   0.000     .5485479     .670202
                              Peru2017  |  -.0572665   .0387336    -1.48   0.139    -.1331829    .0186499
                       Philippines2015  |   .2686214    .067613     3.97   0.000     .1361025    .4011404
                            Poland2019  |  -.1279433   .0654054    -1.96   0.050    -.2561356     .000249
                          Portugal2019  |   -.310178   .0595436    -5.21   0.000    -.4268813   -.1934747
                           Romania2019  |   .4681944   .0407713    11.48   0.000     .3882842    .5481046
                            Russia2019  |   .7687917   .0671498    11.45   0.000     .6371806    .9004028
                           Senegal2014  |   1.726422   .0439863    39.25   0.000      1.64021    1.812633
                       SouthAfrica2020  |  -.3516742   .0399193    -8.81   0.000    -.4299146   -.2734339
                        Southsudan2014  |   1.646932   .1122404    14.67   0.000     1.426945    1.866919
                          SriLanka2011  |   1.148261   .0586368    19.58   0.000     1.033335    1.263187
                            Sweden2020  |   .2509414   .0596349     4.21   0.000     .1340591    .3678237
                          Tanzania2013  |   1.681636   .0713832    23.56   0.000     1.541727    1.821544
                          Thailand2016  |   1.416868   .0353214    40.11   0.000     1.347639    1.486096
                           Tunisia2020  |   2.507868   .0520452    48.19   0.000     2.405862    2.609875
                           Türkiye2019  |  -.4211231   .0247566   -17.01   0.000    -.4696452    -.372601
                            Uganda2013  |   1.203943   .0723268    16.65   0.000     1.062185      1.3457
                           Ukraine2019  |   .6364521   .0634251    10.03   0.000     .5121413     .760763
                        Uzbekistan2019  |   3.039389   .1113135    27.30   0.000     2.821219     3.25756
                           Vietnam2015  |   2.447115   .0822275    29.76   0.000     2.285952    2.608278
                            Zambia2019  |    1.90718   .0582556    32.74   0.000     1.793001    2.021359
                          Zimbabwe2016  |   2.189621    .067767    32.31   0.000       2.0568    2.322442
                                        |
                                 region |
                                   AFR  |          0  (omitted)
                                   EAP  |          0  (omitted)
                                   LAC  |          0  (omitted)
                                   MNA  |          0  (omitted)
                                   SAR  |          0  (omitted)
                                        |
                                   year |
                                  2011  |          0  (omitted)
                                  2012  |          0  (omitted)
                                  2013  |          0  (omitted)
                                  2014  |          0  (omitted)
                                  2015  |          0  (omitted)
                                  2016  |          0  (omitted)
                                  2017  |          0  (omitted)
                                  2018  |          0  (omitted)
                                  2019  |          0  (omitted)
                                  2020  |          0  (omitted)
                                        |
                                  _cons |  -.0454418   .1779288    -0.26   0.798    -.3941758    .3032923
---------------------------------------------------------------------------------------------------------
      As you can observe, when I try to control at country, region and year level, the variables region and year are omitted.

      Thank you in advanced!
      Last edited by Ibai Ostolozaga Falcon; 20 Oct 2022, 02:18.

      Comment

      • #4
        Ibai:
        I guess that it may be due to the fact that you have -i.CountyYear-, -i.Region- and -i.Year-.
        There's duplicated information across the three variables; therefore, Stata has to choose which one to keep in.
        Kind regards,
        Carlo
        (Stata 19.0)

        Comment

        • #5
          Originally posted by Carlo Lazzaro View Post
          Ibai:
          I guess that it may be due to the fact that you have -i.CountyYear-, -i.Region- and -i.Year-.
          There's duplicated information across the three variables; therefore, Stata has to choose which one to keep in.
          Carlo,

          Thank you again. Even if I replace my variable i.country by i.Country, I get the same problem.

          Code:
            
 logit fin11  lcar1 k7 b8 exporter ownership location sector  i.size i.k9 i.Country i.region i.year if country!=128 & country!=259, vce(cluster country) 

note: 2.region omitted because of collinearity.
note: 3.region omitted because of collinearity.
note: 4.region omitted because of collinearity.
note: 5.region omitted because of collinearity.
note: 6.region omitted because of collinearity.
note: 2011.year omitted because of collinearity.
note: 2012.year omitted because of collinearity.
note: 2013.year omitted because of collinearity.
note: 2014.year omitted because of collinearity.
note: 2015.year omitted because of collinearity.
note: 2016.year omitted because of collinearity.
note: 2017.year omitted because of collinearity.
note: 2018.year omitted because of collinearity.
note: 2019.year omitted because of collinearity.
note: 2020.year omitted because of collinearity.
Iteration 0:   log pseudolikelihood = -12015.957  
Iteration 1:   log pseudolikelihood = -10517.658  
Iteration 2:   log pseudolikelihood = -10456.646  
Iteration 3:   log pseudolikelihood = -10455.165  
Iteration 4:   log pseudolikelihood = -10455.157  
Iteration 5:   log pseudolikelihood = -10455.157  

Logistic regression                                     Number of obs = 19,284
                                                        Wald chi2(11) =      .
                                                        Prob > chi2   =      .
Log pseudolikelihood = -10455.157                       Pseudo R2     = 0.1299

                                                          (Std. err. adjusted for 60 clusters in country)
---------------------------------------------------------------------------------------------------------
                                        |               Robust
                                  fin11 | Coefficient  std. err.      z    P>|z|     [95% conf. interval]
----------------------------------------+----------------------------------------------------------------
                                  lcar1 |  -.0026255   .0310896    -0.08   0.933    -.0635601    .0583091
                                     k7 |  -.0756322   .0849796    -0.89   0.373    -.2421892    .0909249
                                     b8 |   .1249036   .0599805     2.08   0.037      .007344    .2424633
                               exporter |   .1239388   .0603453     2.05   0.040     .0056641    .2422135
                              ownership |  -.1570133   .0886548    -1.77   0.077    -.3307736     .016747
                               location |   -.073328   .0710741    -1.03   0.302    -.2126306    .0659746
                                 sector |   -.036006   .0722839    -0.50   0.618    -.1776798    .1056678
                                        |
                                   size |
                         Medium(20-99)  |    .236467    .067902     3.48   0.000     .1033816    .3695524
                   Large(100 And Over)  |   .2802615   .0597594     4.69   0.000     .1631353    .3973878
                                        |
                                     k9 |
State-owned banks or government agency  |    .205899   .1349049     1.53   0.127    -.0585098    .4703077
       Non-bank financial institutions  |  -.5018669   .1400135    -3.58   0.000    -.7762883   -.2274456
                                 Other  |  -1.448172   .2553297    -5.67   0.000    -1.948609   -.9477345
                                        |
                                Country |
                               Armenia  |   .8410564   .0679515    12.38   0.000     .7078739    .9742389
                            Bangladesh  |   1.940747   .0560378    34.63   0.000     1.830915    2.050578
                               Belarus  |   1.088805   .0677292    16.08   0.000     .9560579    1.221552
                               Belgium  |  -.7362627   .0534814   -13.77   0.000    -.8410843   -.6314411
                              Bulgaria  |   .9418924   .0674681    13.96   0.000     .8096574    1.074127
                                 Chile  |  -.2639994   .0227351   -11.61   0.000    -.3085594   -.2194393
                                 China  |   1.024723   .0985069    10.40   0.000      .831653    1.217793
                              Colombia  |  -.3156425   .0340164    -9.28   0.000    -.3823135   -.2489716
                      Congo, Dem. Rep.  |   .9636231   .0591854    16.28   0.000     .8476219    1.079624
                            Costa Rica  |   2.361854   .0622416    37.95   0.000     2.239863    2.483846
                        Czech Republic  |   1.085682   .0504358    21.53   0.000     .9868301    1.184535
                               Denmark  |   .8046452   .0573559    14.03   0.000     .6922297    .9170608
                      Egypt, Arab Rep.  |   2.189421   .0855738    25.59   0.000       2.0217    2.357143
                           El Salvador  |    1.44403   .0393105    36.73   0.000     1.366983    1.521077
                              Ethiopia  |   1.999711   .0552656    36.18   0.000     1.891392    2.108029
                               Finland  |   1.285555   .0540564    23.78   0.000     1.179606    1.391504
                               Georgia  |   1.458506   .0769581    18.95   0.000     1.307671    1.609341
                                 Ghana  |   1.342579   .0453909    29.58   0.000     1.253615    1.431544
                                Greece  |    1.32009   .0691377    19.09   0.000     1.184583    1.455598
                               Hungary  |   .5087644   .0556327     9.15   0.000     .3997263    .6178025
                                 India  |   1.276626   .1067755    11.96   0.000      1.06735    1.485902
                             Indonesia  |   1.920738   .0813155    23.62   0.000     1.761362    2.080113
                               Ireland  |  -.2752492   .0561551    -4.90   0.000    -.3853112   -.1651872
                                 Italy  |   .1866117   .0570452     3.27   0.001     .0748051    .2984183
                                Jordan  |   2.379368   .0486427    48.92   0.000      2.28403    2.474706
                            Kazakhstan  |   1.341468   .0695795    19.28   0.000     1.205095    1.477841
                                 Kenya  |    1.06159   .0379502    27.97   0.000     .9872084    1.135971
                               Lebanon  |   1.598772   .0448688    35.63   0.000     1.510831    1.686713
                                Malawi  |   3.072267    .043724    70.27   0.000      2.98657    3.157965
                              Malaysia  |  -.2524353   .0440109    -5.74   0.000    -.3386951   -.1661754
                                Mexico  |   .0801382   .0472885     1.69   0.090    -.0125456     .172822
                               Morocco  |   .2515013   .0476869     5.27   0.000     .1580367     .344966
                            Mozambique  |   2.857745   .0711215    40.18   0.000     2.718349     2.99714
                               Myanmar  |   3.483534    .078615    44.31   0.000     3.329452    3.637617
                               Namibia  |   .0825441   .0507886     1.63   0.104    -.0169997    .1820879
                           Netherlands  |   .9782813   .0586364    16.68   0.000     .8633561    1.093207
                               Nigeria  |   2.219756   .1162971    19.09   0.000     1.991818    2.447694
                              Pakistan  |   .6093749   .0310348    19.64   0.000     .5485479     .670202
                                  Peru  |  -.0572665   .0387336    -1.48   0.139    -.1331829    .0186499
                           Philippines  |   .2686214    .067613     3.97   0.000     .1361025    .4011404
                                Poland  |  -.1279433   .0654054    -1.96   0.050    -.2561356     .000249
                              Portugal  |   -.310178   .0595436    -5.21   0.000    -.4268813   -.1934747
                               Romania  |   .4681944   .0407713    11.48   0.000     .3882842    .5481046
                    Russian Federation  |   .7687917   .0671498    11.45   0.000     .6371806    .9004028
                               Senegal  |   1.726422   .0439863    39.25   0.000      1.64021    1.812633
                          South Africa  |  -.3516742   .0399193    -8.81   0.000    -.4299146   -.2734339
                           South Sudan  |   1.646932   .1122404    14.67   0.000     1.426945    1.866919
                             Sri Lanka  |   1.148261   .0586368    19.58   0.000     1.033335    1.263187
                                Sweden  |   .2509414   .0596349     4.21   0.000     .1340591    .3678237
                              Tanzania  |   1.681636   .0713832    23.56   0.000     1.541727    1.821544
                              Thailand  |   1.416868   .0353214    40.11   0.000     1.347639    1.486096
                               Tunisia  |   2.507868   .0520452    48.19   0.000     2.405862    2.609875
                               Turkiye  |  -.4211231   .0247566   -17.01   0.000    -.4696452    -.372601
                                Uganda  |   1.203943   .0723268    16.65   0.000     1.062185      1.3457
                               Ukraine  |   .6364521   .0634251    10.03   0.000     .5121413     .760763
                            Uzbekistan  |   3.039389   .1113135    27.30   0.000     2.821219     3.25756
                               Vietnam  |   2.447115   .0822275    29.76   0.000     2.285952    2.608278
                                Zambia  |    1.90718   .0582556    32.74   0.000     1.793001    2.021359
                              Zimbabwe  |   2.189621    .067767    32.31   0.000       2.0568    2.322442
                                        |
                                 region |
                                   AFR  |          0  (omitted)
                                   EAP  |          0  (omitted)
                                   LAC  |          0  (omitted)
                                   MNA  |          0  (omitted)
                                   SAR  |          0  (omitted)
                                        |
                                   year |
                                  2011  |          0  (omitted)
                                  2012  |          0  (omitted)
                                  2013  |          0  (omitted)
                                  2014  |          0  (omitted)
                                  2015  |          0  (omitted)
                                  2016  |          0  (omitted)
                                  2017  |          0  (omitted)
                                  2018  |          0  (omitted)
                                  2019  |          0  (omitted)
                                  2020  |          0  (omitted)
                                        |
                                  _cons |  -.0454418   .1779288    -0.26   0.798    -.3941758    .3032923
---------------------------------------------------------------------------------------------------------
          As far as I know, it could be related with the matrix X? That is, could be region and year dummy variables linear combinations of country dummies?

          Comment

          • #6
            Ibai:
            yes, I think so.
            As an aside, since you have panel data, why not going -xtlogit-?
            Kind regards,
            Carlo
            (Stata 19.0)

            Comment

            Previous Next
            Working...
            X