Fixed effects estimator
allows for differing intercepts by cross-sectional unit
slope standard errors in parentheses, p-values in brackets

           const:         6,6074       (0,39456)       [0,00000]
           LNASS:         0,4349      (0,022585)       [0,00000]
          RECINV:        0,34128       (0,12214)       [0,00524]
             CUR:      -0,027719     (0,0061381)       [0,00001]
             LEV:       0,071325      (0,055019)       [0,19496]
             ROA:       -0,20614      (0,065829)       [0,00176]
           DLOSS:       0,032679       (0,01626)       [0,04456]
         DFORSAL:       0,049592       (0,02263)       [0,02850]
            LSEG:       0,077627      (0,034201)       [0,02330]
          GROWTH:      -0,019282      (0,010154)       [0,05769]
          TENURE:     -0,0094001      (0,011788)       [0,42526]
         DBIG4_5:        0,18103      (0,039929)       [0,00001]
          AUDCHG:       -0,11725      (0,022859)       [0,00000]
          REPLAG:     0,00030109    (0,00013937)       [0,03084]
             AS5:      -0,011482      (0,017531)       [0,51254]
              MW:        0,10154      (0,017704)       [0,00000]
           DMERG:      -0,022054      (0,011487)       [0,05498]
           DYEND:        0,33957      (0,089303)       [0,00015]
             foo:       0,095379       (0,03812)       [0,01241]
             D04:      0,0023317      (0,069126)       [0,97309]
             D05:      0,0046738        (0,0618)       [0,93972]
             D06:       0,021454      (0,057356)       [0,70840]
             D07:       0,016276      (0,051073)       [0,74999]

1576 group means were subtracted from the data

Residual variance: 110,357/(4220 - 1598) = 0,042089
Joint significance of differing group means:
 F(1575, 2622) = 15,4858 with p-value 0
(A low p-value counts against the null hypothesis that the pooled OLS model
is adequate, in favor of the fixed effects alternative.)


Breusch-Pagan test statistic:
 LM = 2275,35 with p-value = prob(chi-square(1) > 2275,35) = 0
(A low p-value counts against the null hypothesis that the pooled OLS model
is adequate, in favor of the random effects alternative.)

Variance estimators:
 between = 0,281655
 within = 0,042089
Panel is unbalanced: theta varies across units

                         Random effects estimator
           allows for a unit-specific component to the error term
           (standard errors in parentheses, p-values in brackets)

           const:         5,6954       (0,31693)       [0,00000]
           LNASS:        0,50572     (0,0087555)       [0,00000]
          RECINV:        0,50434      (0,076614)       [0,00000]
             CUR:      -0,031458     (0,0051902)       [0,00000]
             LEV:       0,096178      (0,045638)       [0,03514]
             ROA:       -0,24689      (0,060928)       [0,00005]
           DLOSS:       0,051755      (0,015827)       [0,00108]
         DFORSAL:        0,13103      (0,019098)       [0,00000]
            LSEG:        0,19573      (0,022788)       [0,00000]
          GROWTH:       -0,02402     (0,0075175)       [0,00141]
          TENURE:      -0,011581      (0,010154)       [0,25414]
         DBIG4_5:        0,18826      (0,031176)       [0,00000]
          AUDCHG:       -0,11699      (0,022155)       [0,00000]
          REPLAG:     0,00018494    (0,00012933)       [0,15281]
             AS5:      -0,014385      (0,017524)       [0,41178]
              MW:        0,12663      (0,017349)       [0,00000]
        Dagicult:       -0,50313       (0,31789)       [0,11357]
         Dmining:       -0,36437       (0,27877)       [0,19126]
           Dfood:       -0,32909       (0,27754)       [0,23580]
       Dtextiles:       -0,25416       (0,27294)       [0,35181]
          Ddrugs:       -0,11498       (0,27239)       [0,67297]
           Dchem:       -0,12757       (0,27465)       [0,64233]
          Drefin:       -0,47879       (0,27546)       [0,08226]
          Drubbr:       -0,28683       (0,27341)       [0,29421]
         Dindust:      -0,025611       (0,27217)       [0,92504]
         Delectr:      -0,036242       (0,27696)       [0,89590]
         Dmisceq:      -0,029993       (0,27184)       [0,91215]
          Dcompu:      -0,090078       (0,27104)       [0,73964]
         Dtransp:       -0,56096       (0,27327)       [0,04016]
           Dutil:       -0,65252       (0,27412)       [0,01734]
         Dretail:       -0,42687       (0,27099)       [0,11528]
           Dbank:       -0,37254       (0,29874)       [0,21245]
         Dservic:      -0,081487        (0,2749)       [0,76692]
           DMERG:      -0,022074      (0,011044)       [0,04570]
           DYEND:      0,0098951      (0,031155)       [0,75079]
             foo:       0,076314      (0,037294)       [0,04079]
             D04:      -0,022507      (0,064827)       [0,72847]
             D05:      -0,025821      (0,059037)       [0,66186]
             D06:      -0,016435      (0,055818)       [0,76844]
             D07:      -0,026001      (0,050195)       [0,60448]

Hausman test statistic:
 H = 248,702 with p-value = prob(chi-square(22) > 248,702) = 2,61785e-040
(A low p-value counts against the null hypothesis that the random effects
model is consistent, in favor of the fixed effects model.)