I'm running a Heckman selection model based on a heckprob. I have some categorical variables such as grup_ha grupo_edad niveleducativo and the rest of them are dichotomous variables.
I can notice in my results that only approximately 15% of the sample are uncensored observations. So I'm not sure whether this is helping to explatin the whole behavior. Even more so if the model is appropiate.
Because χ 2 = 57.35, this clearly justifies the Heckman selection equation with these data, but I'm not sure yet about it and I can't find much literature about this kind of model. Could anyone tell me how to Interpret these heckprobit results? I suppose I have to interpret as a probit model.
Thank you!
Code:
. heckprob cred_o_fin_aprob i.regiones_co sexo tenenciapropia cuidadotierrayanim existeinfraestructura acceso_sistderiego accesoenergia desti > noventa recibir_asistenciaoasesoria grup_ha niveleducativo grupo_edad, select( soli_cred_o_fin2013=grup_ha sexo grupo_edad sabeleeryesc) vc > e(robust) Fitting probit model: Iteration 0: log pseudolikelihood = -31412.985 Iteration 1: log pseudolikelihood = -30745.027 Iteration 2: log pseudolikelihood = -30740.017 Iteration 3: log pseudolikelihood = -30740.017 Fitting selection model: Iteration 0: log pseudolikelihood = -245658.48 Iteration 1: log pseudolikelihood = -242017.34 Iteration 2: log pseudolikelihood = -241997.85 Iteration 3: log pseudolikelihood = -241997.85 Fitting starting values: Iteration 0: log pseudolikelihood = -61035.075 Iteration 1: log pseudolikelihood = -30953.04 Iteration 2: log pseudolikelihood = -30710.317 Iteration 3: log pseudolikelihood = -30709.844 Iteration 4: log pseudolikelihood = -30709.844 Fitting full model: Iteration 0: log pseudolikelihood = -272920.09 Iteration 1: log pseudolikelihood = -272709.04 (not concave) Iteration 2: log pseudolikelihood = -272708.68 (backed up) Iteration 3: log pseudolikelihood = -272707.97 Iteration 4: log pseudolikelihood = -272707.92 Iteration 5: log pseudolikelihood = -272707.91 Iteration 6: log pseudolikelihood = -272707.91 Probit model with sample selection Number of obs = 571,952 Censored obs = 483,897 Uncensored obs = 88,055 Wald chi2(15) = 1092.15 Log pseudolikelihood = -272707.9 Prob > chi2 = 0.0000 --------------------------------------------------------------------------------------------- | Robust | Coef. Std. Err. z P>|z| [95% Conf. Interval] ----------------------------+---------------------------------------------------------------- cred_o_fin_aprob | regiones_co | Caribe | -.3207418 .0201058 -15.95 0.000 -.3601483 -.2813352 Pacifico | .075082 .0145369 5.16 0.000 .0465902 .1035738 Oriental | .1377078 .0150459 9.15 0.000 .1082184 .1671973 Orinoco-Amazonia | -.2023915 .0241538 -8.38 0.000 -.2497322 -.1550508 | sexo | -.0885042 .0142334 -6.22 0.000 -.1164013 -.0606072 tenenciapropia | .0716722 .0120028 5.97 0.000 .0481471 .0951974 cuidadotierrayanim | .1055903 .0179416 5.89 0.000 .0704253 .1407552 existeinfraestructura | .0249654 .0102271 2.44 0.015 .0049206 .0450102 acceso_sistderiego | .0202652 .0134314 1.51 0.131 -.0060599 .0465903 accesoenergia | .0666022 .0110267 6.04 0.000 .0449903 .0882141 destinoventa | -.0020524 .01243 -0.17 0.869 -.0264148 .0223099 recibir_asistenciaoasesoria | .111292 .0118058 9.43 0.000 .0881531 .1344309 grup_ha | -.8661633 .8533362 -1.02 0.310 -2.538672 .8063449 niveleducativo | -.0214992 .0051078 -4.21 0.000 -.0315102 -.0114881 grupo_edad | -.0740636 .0065678 -11.28 0.000 -.0869362 -.061191 _cons | 2.724741 .8553536 3.19 0.001 1.048278 4.401203 ----------------------------+---------------------------------------------------------------- soli_cred_o_fin2013 | grup_ha | -.0262168 .4370274 -0.06 0.952 -.8827748 .8303412 sexo | .1801206 .0046461 38.77 0.000 .1710145 .1892267 grupo_edad | .0252196 .002117 11.91 0.000 .0210703 .0293689 sabeleeryesc | .4375166 .0060783 71.98 0.000 .4256034 .4494298 _cons | -1.567543 .4371122 -3.59 0.000 -2.424268 -.7108193 ----------------------------+---------------------------------------------------------------- /athrho | -.4703892 .0621132 -7.57 0.000 -.5921288 -.3486496 ----------------------------+---------------------------------------------------------------- rho | -.4385137 .0501692 -.5314249 -.3351774 --------------------------------------------------------------------------------------------- Wald test of indep. eqns. (rho = 0): chi2(1) = 57.35 Prob > chi2 = 0.0000 end
0 Response to Doubt on Heckprob model results
Post a Comment