Announcement

Collapse
No announcement yet.
X
  • Filter
  • Time
  • Show
Clear All
new posts

  • panel data regression results with country- and year-fixed effects

    Hi (all),

    I have been trying to solve this issue for a few days now. Unfortunately, I did not find a solution that works. Therefore, let me try here:

    I am running a panel data regression for 63 countries and 23 years (1996-2018). My independent variable is 'socio-economic development', comprised of three seperate (predictor) variables 'GDPlog' 'LifeExpectancy', and 'Urbanization rate'. I have lagged these independent variables. My dependent variable is a computed proxy for 'Individualism' (data gathered from the World Value Survey - which is aggregated to the country level).

    After running the model with both time- and country-fixed effects, a lot of values turn out insignificant (see output). In this regression, 'IQ' (institutional quality) and 'EI' (Economic Inequality) serve as a moderator. For this regression, however, I have not yet created the interaction effects. The variables 'PS', 'HD', and 'GEN' are control variables.

    I would greatly appreciate all the help!! (I am quite the rookie).

    Thank you!

    Code:
    . xtreg IDV lnGDPpw lnLE lnURB IQ EI PS HD GEN i.Year, fe
    
    Fixed-effects (within) regression               Number of obs     =        687
    Group variable: ID                              Number of groups  =         60
    
    R-squared:                                      Obs per group:
         Within  = 0.2229                                         min =          1
         Between = 0.0022                                         avg =       11.4
         Overall = 0.0027                                         max =         19
    
                                                    F(27,600)         =       6.37
    corr(u_i, Xb) = -0.3502                         Prob > F          =     0.0000
    
    ------------------------------------------------------------------------------
             IDV | Coefficient  Std. err.      t    P>|t|     [95% conf. interval]
    -------------+----------------------------------------------------------------
         lnGDPpw |  -.0149985   .0320457    -0.47   0.640    -.0779338    .0479368
            lnLE |  -.0235256   .0470972    -0.50   0.618     -.116021    .0689698
           lnURB |   .0417426   .0133699     3.12   0.002     .0154852    .0680001
              IQ |   .0129416   .0038266     3.38   0.001     .0054265    .0204568
              EI |   .0664247   .0426652     1.56   0.120    -.0173666    .1502159
              PS |  -6.02e-11   3.28e-11    -1.84   0.067    -1.25e-10    4.14e-12
              HD |  -.1772328   .0423389    -4.19   0.000    -.2603832   -.0940823
             GEN |  -.0034419   .0024012    -1.43   0.152    -.0081578    .0012739
                 |
            Year |
           1998  |  -.0452868   .0128549    -3.52   0.000    -.0705329   -.0200407
           1999  |  -.0487066   .0127952    -3.81   0.000    -.0738353   -.0235779
           2000  |  -.0485705   .0127925    -3.80   0.000     -.073694    -.023447
           2001  |  -.0475299   .0127604    -3.72   0.000    -.0725904   -.0224694
           2002  |  -.0463023   .0127169    -3.64   0.000    -.0712774   -.0213272
           2003  |  -.0451734   .0126634    -3.57   0.000    -.0700433   -.0203034
           2004  |  -.0440253   .0126264    -3.49   0.001    -.0688227   -.0192279
           2005  |  -.0470253   .0124831    -3.77   0.000    -.0715412   -.0225095
           2006  |  -.0457833   .0124636    -3.67   0.000    -.0702609   -.0213058
           2007  |  -.0447061   .0124359    -3.59   0.000    -.0691293   -.0202829
           2008  |  -.0438945   .0124104    -3.54   0.000    -.0682676   -.0195214
           2009  |  -.0433583   .0124209    -3.49   0.001    -.0677521   -.0189646
           2010  |  -.0442326   .0124327    -3.56   0.000    -.0686496   -.0198156
           2011  |  -.0433819   .0124256    -3.49   0.001    -.0677848   -.0189789
           2012  |  -.0427049   .0124232    -3.44   0.001    -.0671032   -.0183066
           2013  |  -.0418179   .0124166    -3.37   0.001    -.0662032   -.0174325
           2014  |   -.041259   .0124139    -3.32   0.001     -.065639   -.0168789
           2017  |  -.0468404   .0123093    -3.81   0.000     -.071015   -.0226658
           2018  |  -.0462844   .0123093    -3.76   0.000    -.0704589   -.0221098
                 |
           _cons |   1.051972   .2245873     4.68   0.000     .6108988    1.493044
    -------------+----------------------------------------------------------------
         sigma_u |  .04974205
         sigma_e |  .01070822
             rho |  .95570923   (fraction of variance due to u_i)
    ------------------------------------------------------------------------------
    F test that all u_i=0: F(59, 600) = 49.14                    Prob > F = 0.0000

  • #2
    Wessel
    have you already checked (via -estat vce, corr-) that -lnGDPpw- and -lnLE- are not highly correlated?
    Kind regards,
    Carlo
    (Stata 19.0)

    Comment


    • #3
      Thank you for your swift resposne, Carlo!

      They are indeed highly correlated. However, when I checked for 'vif', they all (but 'HD' = 'human development' turned out fine). Also, when I ran a simple correlation matrix (see also coded) the values were quite fine. Stata did not drop a variable from the model, hence I figured it would be fine.

      Would you suggest dropping a variable, or replacing it with another?

      Thank you so much for your help.

      Best,
      Wessel

      Code:
      . estat vce, corr
      
      Correlation matrix of coefficients of xtreg model
      
                   |                                                                           1998.     1999.     2000.     2001.     2002.     2003.     2004.
              e(V) |  lnGDPpw      lnLE     lnURB        IQ        EI        PS        HD      Year      Year      Year      Year      Year      Year      Year 
      -------------+--------------------------------------------------------------------------------------------------------------------------------------------
           lnGDPpw |   1.0000                                                                                                                                   
              lnLE |   0.0401    1.0000                                                                                                                         
             lnURB |  -0.1646    0.0099    1.0000                                                                                                               
                IQ |  -0.1313    0.0023   -0.0538    1.0000                                                                                                     
                EI |   0.1265    0.1219   -0.0154   -0.0229    1.0000                                                                                           
                PS |  -0.0913    0.0186   -0.3121    0.0911    0.2770    1.0000                                                                                 
                HD |  -0.2171   -0.4718   -0.2625    0.0027   -0.1443   -0.1722    1.0000                                                                       
         1998.Year |  -0.1315   -0.2110   -0.0841   -0.0319   -0.0231   -0.0689    0.4515    1.0000                                                             
         1999.Year |  -0.1356   -0.2127   -0.0711   -0.0368   -0.0164   -0.0642    0.4410    0.9805    1.0000                                                   
         2000.Year |  -0.1293   -0.2183   -0.0616   -0.0366   -0.0101   -0.0584    0.4308    0.9738    0.9748    1.0000                                         
         2001.Year |  -0.1268   -0.2249   -0.0644   -0.0325   -0.0045   -0.0565    0.4259    0.9734    0.9745    0.9706    1.0000                               
         2002.Year |  -0.1268   -0.2280   -0.0668   -0.0279    0.0004   -0.0539    0.4187    0.9728    0.9740    0.9702    0.9704    1.0000                     
         2003.Year |  -0.1278   -0.2317   -0.0680   -0.0242   -0.0010   -0.0526    0.4102    0.9719    0.9732    0.9695    0.9700    0.9702    1.0000           
         2004.Year |  -0.1314   -0.2381   -0.0686   -0.0198   -0.0025   -0.0510    0.4031    0.9708    0.9722    0.9686    0.9693    0.9697    0.9699    1.0000 
         2005.Year |  -0.1186   -0.2398   -0.0688   -0.0249    0.0030   -0.0562    0.3859    0.9757    0.9767    0.9723    0.9733    0.9740    0.9746    0.9749 
         2006.Year |  -0.1293   -0.2477   -0.0666   -0.0220    0.0045   -0.0510    0.3781    0.9738    0.9750    0.9708    0.9719    0.9729    0.9737    0.9744 
         2007.Year |  -0.1328   -0.2524   -0.0657   -0.0217    0.0100   -0.0461    0.3688    0.9716    0.9730    0.9690    0.9704    0.9716    0.9726    0.9736 
         2008.Year |  -0.1338   -0.2585   -0.0659   -0.0200    0.0063   -0.0445    0.3616    0.9697    0.9712    0.9673    0.9689    0.9702    0.9715    0.9727 
         2009.Year |  -0.1306   -0.2696   -0.0690   -0.0166    0.0038   -0.0438    0.3608    0.9681    0.9697    0.9659    0.9676    0.9691    0.9706    0.9719 
         2010.Year |  -0.1325   -0.2758   -0.0645   -0.0152   -0.0006   -0.0457    0.3524    0.9633    0.9651    0.9616    0.9634    0.9651    0.9667    0.9683 
         2011.Year |  -0.1320   -0.2857   -0.0621   -0.0196   -0.0015   -0.0443    0.3443    0.9602    0.9622    0.9589    0.9609    0.9627    0.9646    0.9665 
         2012.Year |  -0.1324   -0.2914   -0.0616   -0.0188   -0.0027   -0.0441    0.3396    0.9581    0.9602    0.9570    0.9592    0.9611    0.9632    0.9652 
         2013.Year |  -0.1329   -0.2987   -0.0595   -0.0192   -0.0057   -0.0435    0.3321    0.9550    0.9572    0.9542    0.9565    0.9587    0.9609    0.9631 
         2014.Year |  -0.1313   -0.3046   -0.0580   -0.0249   -0.0061   -0.0433    0.3253    0.9522    0.9546    0.9517    0.9542    0.9564    0.9589    0.9613 
         2017.Year |  -0.1373   -0.3088   -0.0681   -0.0262   -0.0107   -0.0264    0.3103    0.9505    0.9530    0.9499    0.9527    0.9552    0.9580    0.9608 
         2018.Year |  -0.1379   -0.3117   -0.0694   -0.0235   -0.0093   -0.0239    0.3056    0.9483    0.9508    0.9479    0.9508    0.9534    0.9564    0.9593 
             _cons |  -0.2296   -0.9446   -0.1902    0.0414   -0.1707    0.0952    0.4356    0.1429    0.1434    0.1464    0.1536    0.1584    0.1641    0.1728 
      
                   |     2005.     2006.     2007.     2008.     2009.     2010.     2011.     2012.     2013.     2014.     2017.     2018.          
              e(V) |     Year      Year      Year      Year      Year      Year      Year      Year      Year      Year      Year      Year     _cons 
      -------------+----------------------------------------------------------------------------------------------------------------------------------
         2005.Year |   1.0000                                                                                                                         
         2006.Year |   0.9826    1.0000                                                                                                               
         2007.Year |   0.9821    0.9826    1.0000                                                                                                     
         2008.Year |   0.9815    0.9823    0.9826    1.0000                                                                                           
         2009.Year |   0.9809    0.9819    0.9823    0.9826    1.0000                                                                                 
         2010.Year |   0.9770    0.9783    0.9790    0.9795    0.9798    1.0000                                                                       
         2011.Year |   0.9755    0.9771    0.9781    0.9788    0.9793    0.9780    1.0000                                                             
         2012.Year |   0.9745    0.9762    0.9773    0.9782    0.9789    0.9777    0.9781    1.0000                                                   
         2013.Year |   0.9727    0.9748    0.9761    0.9772    0.9780    0.9772    0.9778    0.9780    1.0000                                         
         2014.Year |   0.9711    0.9734    0.9749    0.9762    0.9771    0.9764    0.9773    0.9777    0.9780    1.0000                               
         2017.Year |   0.9712    0.9740    0.9759    0.9776    0.9787    0.9775    0.9788    0.9794    0.9801    0.9805    1.0000                     
         2018.Year |   0.9699    0.9728    0.9748    0.9766    0.9779    0.9768    0.9783    0.9790    0.9797    0.9802    0.9857    1.0000           
             _cons |   0.1734    0.1848    0.1916    0.1994    0.2109    0.2183    0.2289    0.2355    0.2440    0.2504    0.2614    0.2656    1.0000

      Code:
       corr IDV lnGDPpw lnLE lnURB IQ EI PS HD
      (obs=687)
      
                   |      IDV  lnGDPpw     lnLE    lnURB       IQ       EI       PS       HD
      -------------+------------------------------------------------------------------------
               IDV |   1.0000
           lnGDPpw |  -0.6119   1.0000
              lnLE |  -0.6626   0.6343   1.0000
             lnURB |  -0.4809   0.7653   0.6035   1.0000
                IQ |  -0.6568   0.6920   0.5724   0.5338   1.0000
                EI |  -0.6023   0.3724   0.4220   0.1036   0.4833   1.0000
                PS |   0.1177  -0.4356  -0.2630  -0.4468  -0.2579  -0.1003   1.0000
                HD |  -0.7793   0.8752   0.8272   0.7532   0.7272   0.4911  -0.3608   1.0000

      Comment


      • #4
        Wessel:
        what if you omit -lnLE-?
        Kind regards,
        Carlo
        (Stata 19.0)

        Comment


        • #5
          Dear Carlo,

          Thank you again.

          After omitting -lnLE- from the model, I get the following results:

          Unfortunately, I do not see any big difference in the results. I will also include the -VIF- scores for your reference.

          Is there any other way this could be resolved?

          Code:
          . xtreg IDV lnGDPpw lnURB IQ EI PS HD GEN i.Year, fe
          
          Fixed-effects (within) regression               Number of obs     =        689
          Group variable: ID                              Number of groups  =         60
          
          R-squared:                                      Obs per group:
               Within  = 0.2219                                         min =          1
               Between = 0.0088                                         avg =       11.5
               Overall = 0.0070                                         max =         19
          
                                                          F(26,603)         =       6.61
          corr(u_i, Xb) = -0.3038                         Prob > F          =     0.0000
          
          ------------------------------------------------------------------------------
                   IDV | Coefficient  Std. err.      t    P>|t|     [95% conf. interval]
          -------------+----------------------------------------------------------------
               lnGDPpw |  -.0149101   .0320015    -0.47   0.641    -.0777581    .0479379
                 lnURB |    .042208   .0133599     3.16   0.002     .0159705    .0684455
                    IQ |   .0109952   .0036142     3.04   0.002     .0038973    .0180932
                    EI |   .0785723   .0417941     1.88   0.061    -.0035073    .1606519
                    PS |  -5.79e-11   3.27e-11    -1.77   0.077    -1.22e-10    6.33e-12
                    HD |  -.1862652   .0373678    -4.98   0.000     -.259652   -.1128784
                   GEN |   -.003737   .0023932    -1.56   0.119     -.008437     .000963
                       |
                  Year |
                 1998  |  -.0457367   .0125545    -3.64   0.000    -.0703926   -.0210808
                 1999  |  -.0492563   .0124937    -3.94   0.000    -.0737928   -.0247198
                 2000  |  -.0494512   .0124836    -3.96   0.000    -.0739678   -.0249345
                 2001  |  -.0484653   .0124338    -3.90   0.000    -.0728841   -.0240465
                 2002  |  -.0472716   .0123825    -3.82   0.000    -.0715897   -.0229535
                 2003  |  -.0461914   .0123198    -3.75   0.000    -.0703863   -.0219966
                 2004  |  -.0451101    .012265    -3.68   0.000    -.0691974   -.0210228
                 2005  |  -.0480728   .0121177    -3.97   0.000    -.0718709   -.0242748
                 2006  |  -.0468821   .0120737    -3.88   0.000    -.0705938   -.0231704
                 2007  |  -.0458177   .0120313    -3.81   0.000     -.069446   -.0221894
                 2008  |  -.0450661   .0119866    -3.76   0.000    -.0686066   -.0215255
                 2009  |  -.0446346   .0119594    -3.73   0.000    -.0681217   -.0211476
                 2010  |  -.0455353   .0119477    -3.81   0.000    -.0689994   -.0220712
                 2011  |  -.0447233   .0119045    -3.76   0.000    -.0681026   -.0213439
                 2012  |  -.0440914    .011881    -3.71   0.000    -.0674245   -.0207583
                 2013  |  -.0432568   .0118465    -3.65   0.000    -.0665223   -.0199914
                 2014  |  -.0427025   .0118201    -3.61   0.000     -.065916   -.0194891
                 2017  |   -.048332   .0117025    -4.13   0.000    -.0713146   -.0253493
                 2018  |  -.0478103   .0116906    -4.09   0.000    -.0707695   -.0248511
                       |
                 _cons |   .9696514   .1287948     7.53   0.000     .7167105    1.222592
          -------------+----------------------------------------------------------------
               sigma_u |  .04880243
               sigma_e |  .01070596
                   rho |  .95408492   (fraction of variance due to u_i)
          ------------------------------------------------------------------------------
          F test that all u_i=0: F(59, 603) = 49.18                    Prob > F = 0.0000
          
          . estat vce, corr
          
          Correlation matrix of coefficients of xtreg model
          
                       |                                                                           1998.     1999.     2000.     2001.     2002.     2003.     2004.
                  e(V) |  lnGDPpw     lnURB        IQ        EI        PS        HD       GEN      Year      Year      Year      Year      Year      Year      Year 
          -------------+--------------------------------------------------------------------------------------------------------------------------------------------
               lnGDPpw |   1.0000                                                                                                                                   
                 lnURB |  -0.1600    1.0000                                                                                                                         
                    IQ |  -0.1458   -0.0532    1.0000                                                                                                               
                    EI |   0.1296   -0.0134    0.0254    1.0000                                                                                                     
                    PS |  -0.0915   -0.3134    0.1116    0.2719    1.0000                                                                                           
                    HD |  -0.2222   -0.2837    0.0058   -0.0957   -0.1858    1.0000                                                                                 
                   GEN |  -0.0371   -0.0983    0.0181   -0.0659    0.0111   -0.0661    1.0000                                                                       
             1998.Year |  -0.1240   -0.0793   -0.0214    0.0008   -0.0683    0.4098   -0.0447    1.0000                                                             
             1999.Year |  -0.1272   -0.0661   -0.0264    0.0069   -0.0642    0.3978   -0.0514    0.9802    1.0000                                                   
             2000.Year |  -0.1214   -0.0559   -0.0325    0.0174   -0.0571    0.3829   -0.0497    0.9729    0.9739    1.0000                                         
             2001.Year |  -0.1186   -0.0588   -0.0283    0.0242   -0.0551    0.3742   -0.0502    0.9725    0.9736    0.9691    1.0000                               
             2002.Year |  -0.1185   -0.0612   -0.0237    0.0299   -0.0524    0.3645   -0.0510    0.9719    0.9731    0.9687    0.9689    1.0000                     
             2003.Year |  -0.1196   -0.0623   -0.0201    0.0291   -0.0510    0.3529   -0.0511    0.9711    0.9724    0.9681    0.9684    0.9686    1.0000           
             2004.Year |  -0.1233   -0.0631   -0.0159    0.0286   -0.0492    0.3417   -0.0503    0.9701    0.9715    0.9672    0.9677    0.9681    0.9683    1.0000 
             2005.Year |  -0.1107   -0.0648   -0.0201    0.0333   -0.0545    0.3201   -0.0360    0.9752    0.9760    0.9710    0.9718    0.9725    0.9730    0.9733 
             2006.Year |  -0.1216   -0.0628   -0.0169    0.0357   -0.0491    0.3072   -0.0337    0.9733    0.9744    0.9695    0.9705    0.9714    0.9722    0.9728 
             2007.Year |  -0.1253   -0.0622   -0.0162    0.0418   -0.0441    0.2939   -0.0315    0.9712    0.9725    0.9677    0.9689    0.9700    0.9710    0.9718 
             2008.Year |  -0.1264   -0.0628   -0.0147    0.0387   -0.0423    0.2825   -0.0287    0.9694    0.9708    0.9661    0.9674    0.9687    0.9699    0.9709 
             2009.Year |  -0.1232   -0.0662   -0.0115    0.0377   -0.0414    0.2761   -0.0264    0.9683    0.9696    0.9650    0.9664    0.9678    0.9691    0.9703 
             2010.Year |  -0.1253   -0.0621   -0.0095    0.0335   -0.0433    0.2630   -0.0217    0.9635    0.9650    0.9606    0.9621    0.9636    0.9652    0.9665 
             2011.Year |  -0.1248   -0.0600   -0.0139    0.0335   -0.0419    0.2486   -0.0197    0.9607    0.9624    0.9582    0.9598    0.9615    0.9633    0.9649 
             2012.Year |  -0.1252   -0.0595   -0.0131    0.0330   -0.0416    0.2403   -0.0190    0.9589    0.9607    0.9565    0.9583    0.9601    0.9620    0.9637 
             2013.Year |  -0.1257   -0.0575   -0.0136    0.0309   -0.0409    0.2278   -0.0182    0.9562    0.9581    0.9541    0.9560    0.9579    0.9600    0.9619 
             2014.Year |  -0.1240   -0.0560   -0.0194    0.0310   -0.0407    0.2168   -0.0178    0.9537    0.9558    0.9519    0.9539    0.9559    0.9582    0.9602 
             2017.Year |  -0.1308   -0.0678   -0.0209    0.0260   -0.0228    0.1962   -0.0070    0.9519    0.9540    0.9499    0.9521    0.9545    0.9572    0.9596 
             2018.Year |  -0.1315   -0.0693   -0.0181    0.0279   -0.0200    0.1890   -0.0045    0.9498    0.9519    0.9479    0.9502    0.9527    0.9555    0.9581 
                 _cons |  -0.2656   -0.1945    0.0533   -0.0298    0.1659    0.0393   -0.8609   -0.0506   -0.0466   -0.0520   -0.0500   -0.0467   -0.0431   -0.0396 
          
                       |     2005.     2006.     2007.     2008.     2009.     2010.     2011.     2012.     2013.     2014.     2017.     2018.          
                  e(V) |     Year      Year      Year      Year      Year      Year      Year      Year      Year      Year      Year      Year     _cons 
          -------------+----------------------------------------------------------------------------------------------------------------------------------
             2005.Year |   1.0000                                                                                                                         
             2006.Year |   0.9816    1.0000                                                                                                               
             2007.Year |   0.9810    0.9815    1.0000                                                                                                     
             2008.Year |   0.9804    0.9811    0.9814    1.0000                                                                                           
             2009.Year |   0.9800    0.9808    0.9812    0.9814    1.0000                                                                                 
             2010.Year |   0.9761    0.9771    0.9777    0.9780    0.9781    1.0000                                                                       
             2011.Year |   0.9748    0.9761    0.9769    0.9775    0.9777    0.9762    1.0000                                                             
             2012.Year |   0.9739    0.9754    0.9763    0.9770    0.9773    0.9759    0.9761    1.0000                                                   
             2013.Year |   0.9724    0.9741    0.9753    0.9762    0.9766    0.9754    0.9758    0.9759    1.0000                                         
             2014.Year |   0.9711    0.9729    0.9743    0.9753    0.9758    0.9748    0.9754    0.9756    0.9758    1.0000                               
             2017.Year |   0.9712    0.9736    0.9754    0.9768    0.9775    0.9759    0.9770    0.9775    0.9781    0.9784    1.0000                     
             2018.Year |   0.9699    0.9724    0.9744    0.9759    0.9767    0.9752    0.9764    0.9770    0.9777    0.9781    0.9841    1.0000           
                 _cons |  -0.0536   -0.0494   -0.0477   -0.0470   -0.0475   -0.0493   -0.0490   -0.0478   -0.0462   -0.0453   -0.0431   -0.0431    1.0000
          Code:
          . vif
          
              Variable |       VIF       1/VIF  
          -------------+----------------------
                    HD |     11.55    0.086587
               lnGDPpw |      5.82    0.171715
                  lnLE |      3.70    0.270170
                 lnURB |      3.46    0.289193
                    IQ |      2.32    0.430490
                    EI |      1.78    0.562900
                    PS |      1.50    0.666135
                   GEN |      1.43    0.701289
          -------------+----------------------
              Mean VIF |      3.94

          Comment


          • #6
            Wessel:
            as -HD- seems to have a pretty wide 95%CI, what if:
            Code:
             
             xtreg IDV lnGDPpw lnURB IQ EI PS GEN i.Year, fe vce(cluster panelid)
            Kind regards,
            Carlo
            (Stata 19.0)

            Comment


            • #7
              Hi Carlo,

              Thank you for yet another good suggestion.

              However, when clustering my panelid, I get the following results:

              I am really not sure what to do now. Can you tell if I am doing this right?

              Thank you again. I really appreciate it.

              [CODE] xtreg IDV lnGDPpw lnURB IQ EI PS GEN i.Year, fe vce(cluster ID)

              Fixed-effects (within) regression Number of obs = 768
              Group variable: ID Number of groups = 60

              R-squared: Obs per group:
              Within = 0.1755 min = 2
              Between = 0.1703 avg = 12.8
              Overall = 0.1138 max = 21

              F(25,59) = .
              corr(u_i, Xb) = -0.7140 Prob > F = .

              (Std. err. adjusted for 60 clusters in ID)
              ------------------------------------------------------------------------------
              | Robust
              IDV | Coefficient std. err. t P>|t| [95% conf. interval]
              -------------+----------------------------------------------------------------
              lnGDPpw | -.0438557 .0489124 -0.90 0.374 -.1417292 .0540178
              lnURB | .0125974 .0348042 0.36 0.719 -.0570456 .0822404
              IQ | .0080377 .0072877 1.10 0.275 -.0065449 .0226203
              EI | .0738442 .0778357 0.95 0.347 -.0819046 .2295931
              PS | -8.94e-11 3.98e-11 -2.24 0.029 -1.69e-10 -9.68e-12
              GEN | -.0013909 .0059851 -0.23 0.817 -.0133671 .0105853
              |
              Year |
              1997 | .0002143 .0002351 0.91 0.366 -.0002562 .0006848
              1998 | .0015002 .0013439 1.12 0.269 -.0011889 .0041892
              1999 | -.0022971 .0030448 -0.75 0.454 -.0083896 .0037955
              2000 | -.0032519 .0040376 -0.81 0.424 -.0113311 .0048273
              2001 | -.002861 .0040361 -0.71 0.481 -.0109373 .0052152
              2002 | -.0023371 .004061 -0.58 0.567 -.0104632 .0057891
              2003 | -.0020826 .0040616 -0.51 0.610 -.0102098 .0060445
              2004 | -.0017714 .0041191 -0.43 0.669 -.0100137 .006471
              2005 | -.0063851 .0034818 -1.83 0.072 -.0133521 .0005819
              2006 | -.0060079 .0034905 -1.72 0.090 -.0129924 .0009766
              2007 | -.0057188 .003583 -1.60 0.116 -.0128883 .0014507
              2008 | -.0056763 .0036541 -1.55 0.126 -.0129882 .0016355
              2009 | -.0056224 .0037181 -1.51 0.136 -.0130623 .0018176
              2010 | -.0065587 .0038577 -1.70 0.094 -.014278 .0011606
              2011 | -.0065695 .0039394 -1.67 0.101 -.0144521 .0013132
              2012 | -.0064407 .004004 -1.61 0.113 -.0144527 .0015712
              2013 | -.0063717 .0040794 -1.56 0.124 -.0145346 .0017912
              2014 | -.0064124 .004159 -1.54 0.128 -.0147345 .0019098
              2017 | -.0135504 .0054362 -2.49 0.016 -.0244282 -.0026725
              2018 | -.0134157 .0055284 -2.43 0.018 -.0244781 -.0023533
              |
              _cons | .8452412 .34273 2.47 0.017 .15944 1.531042
              -------------+----------------------------------------------------------------
              sigma_u | .06071996
              sigma_e | .01168254
              rho | .96430354 (fraction of variance due to u_i)
              ------------------------------------------------------------------------------
              /CODE]

              Comment


              • #8
                Wessel:
                1) the missingness of the F-test is explained at -help j_robustsingular-;
                2) what strikes here is that cluster-robust standard errors (60 groups are enough to go this way) give back a totally different story, which is probably the most reliable one (within-panel serial correlation of epsilon);
                3) I would try without logging at all your independent variables;
                4) aftre that, I would also check whether the functional form of the regressand is correctly specified, including -fitted- and -sq_fitted- values as predictors of an augmente regression (see -linktest- entry in Stata .pdf manual).
                Kind regards,
                Carlo
                (Stata 19.0)

                Comment

                Working...
                X