Announcement

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

  • Two equations of xtabond not equivalent

    Hello
    I am studying about the dynamic panel with `xtabond`

    According to Stata manual xtxtabond.pdf (stata.com)

    Code:
    xtabond n l(0/1).w l(0/2).(k ys) yr1980-yr1984 year, lags(2) noconstant
    Output:
    Code:
    Arellano–Bond dynamic panel-data estimation     Number of obs     =        611
    Group variable: id                              Number of groups  =        140
    Time variable: year
                                                    Obs per group:
                                                                  min =          4
                                                                  avg =   4.364286
                                                                  max =          6
    
    Number of instruments =     41                  Wald chi2(16)     =    1757.07
                                                    Prob > chi2       =     0.0000
    One-step results
    ------------------------------------------------------------------------------
               n | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
    -------------+----------------------------------------------------------------
               n |
             L1. |   .6862261   .1486163     4.62   0.000     .3949435    .9775088
             L2. |  -.0853582   .0444365    -1.92   0.055    -.1724523    .0017358
                 |
               w |
             --. |  -.6078208   .0657694    -9.24   0.000    -.7367265   -.4789151
             L1. |   .3926237   .1092374     3.59   0.000     .1785222    .6067251
                 |
               k |
             --. |   .3568456   .0370314     9.64   0.000     .2842653    .4294259
             L1. |  -.0580012   .0583051    -0.99   0.320     -.172277    .0562747
             L2. |  -.0199475   .0416274    -0.48   0.632    -.1015357    .0616408
                 |
              ys |
             --. |   .6085073   .1345412     4.52   0.000     .3448115    .8722031
             L1. |  -.7111651   .1844599    -3.86   0.000      -1.0727   -.3496304
             L2. |   .1057969   .1428568     0.74   0.459    -.1741974    .3857912
                 |
          yr1980 |   .0029062   .0212705     0.14   0.891    -.0387832    .0445957
          yr1981 |  -.0404378   .0354707    -1.14   0.254    -.1099591    .0290836
          yr1982 |  -.0652767    .048209    -1.35   0.176    -.1597646    .0292111
          yr1983 |  -.0690928   .0627354    -1.10   0.271    -.1920521    .0538664
          yr1984 |  -.0650302   .0781322    -0.83   0.405    -.2181665    .0881061
            year |   .0095545   .0142073     0.67   0.501    -.0182912    .0374002
    ------------------------------------------------------------------------------
    Instruments for differenced equation
            GMM-type: L(2/.).n
            Standard: D.w LD.w D.k LD.k L2D.k D.ys LD.ys L2D.ys D.yr1980
                      D.yr1981 D.yr1982 D.yr1983 D.yr1984 D.year

    However, when I try to run a similar code

    Code:
    xtabond n l.n l2.n w l.w k l.k l2.k ys l.ys l2.ys yr1980-yr1984 year, noconstant
    Output:
    Code:
    note: L.n omitted because of collinearity.
    
    Arellano–Bond dynamic panel-data estimation     Number of obs     =        611
    Group variable: id                              Number of groups  =        140
    Time variable: year
                                                    Obs per group:
                                                                  min =          4
                                                                  avg =   4.364286
                                                                  max =          6
    
    Number of instruments =     42                  Wald chi2(16)     =    2244.24
                                                    Prob > chi2       =     0.0000
    One-step results
    ------------------------------------------------------------------------------
               n | Coefficient  Std. err.      z    P>|z|     [95% conf. interval]
    -------------+----------------------------------------------------------------
               n |
             L1. |   .1653985   .0417079     3.97   0.000     .0836526    .2471444
             L2. |  -.0630636   .0389283    -1.62   0.105    -.1393617    .0132345
                 |
               w |
             --. |  -.5501356   .0564937    -9.74   0.000    -.6608611     -.43941
             L1. |   .0830758   .0620022     1.34   0.180    -.0384463     .204598
                 |
               k |
             --. |   .3888834   .0318344    12.22   0.000     .3264892    .4512777
             L1. |   .1036699   .0340821     3.04   0.002     .0368701    .1704696
             L2. |   .0543961   .0322247     1.69   0.091    -.0087632    .1175554
                 |
              ys |
             --. |   .5090537   .1165611     4.37   0.000     .2805982    .7375093
             L1. |  -.3438416   .1374004    -2.50   0.012    -.6131414   -.0745419
             L2. |   .0262095   .1248746     0.21   0.834    -.2185403    .2709593
                 |
          yr1980 |   .0083141   .0187634     0.44   0.658    -.0284615    .0450898
          yr1981 |  -.0185371   .0309234    -0.60   0.549    -.0791459    .0420717
          yr1982 |  -.0345602   .0419894    -0.82   0.410     -.116858    .0477376
          yr1983 |   -.026483   .0545276    -0.49   0.627    -.1333551    .0803892
          yr1984 |  -.0044671     .06755    -0.07   0.947    -.1368627    .1279285
            year |  -.0056971   .0120208    -0.47   0.636    -.0292574    .0178632
    ------------------------------------------------------------------------------
    Instruments for differenced equation
            GMM-type: L(2/.).n
            Standard: LD.n L2D.n D.w LD.w D.k LD.k L2D.k D.ys LD.ys L2D.ys
                      D.yr1980 D.yr1981 D.yr1982 D.yr1983 D.yr1984 D.year
    I don't know why the result is different.

  • #2
    The standard instruments are different.

    Comment

    Working...
    X