[Gretl-users] Re: Missing value handling and correlated random effects CRE model

I think I forgot to add the original variables. Model 5: Random-effects (GLS), using 28101 observations Included 4699 cross-sectional units Time-series length: minimum 1, maximum 15 Dependent variable: ln_wage Standard errors clustered by unit coefficient std. error z p-value ------------------------------------------------------------ const 1.21574 0.0307699 39.51 0.0000 *** tm_tenure 0.0376962 0.00228348 16.51 3.20e-061 *** tm_age −0.00119223 0.00133533 −0.8928 0.3719 tenure 0.0211328 0.00121105 17.45 3.44e-068 *** age 0.0121935 0.000741173 16.45 8.16e-061 *** Drace_2 −0.131206 0.0117850 −11.13 8.64e-029 *** Drace_3 0.105973 0.0593175 1.787 0.0740 * Mean dependent var 1.677104 S.D. dependent var 0.477798 Sum squared resid 5204.450 S.E. of regression 0.430401 Log-likelihood −16180.36 Akaike criterion 32374.72 Schwarz criterion 32432.42 Hannan-Quinn 32393.29 rho 0.234207 Durbin-Watson 1.126737 'Between' variance = 0.111147 'Within' variance = 0.0888528 mean theta = 0.604243 corr(y,yhat)^2 = 0.189022 Joint test on named regressors - Asymptotic test statistic: Chi-square(6) = 2688.49 with p-value = 0 Breusch-Pagan test - Null hypothesis: Variance of the unit-specific error = 0 Asymptotic test statistic: Chi-square(1) = 23021.3 with p-value = 0 Hausman test - Null hypothesis: GLS estimates are consistent Asymptotic test statistic: Chi-square(1) = 0.0284789 with p-value = 0.865988