Announcement

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

  • oaxaca_riff

    Dear members,
    I am trying to estimate productivity/yield gap between men and women using oaxaca_rif. The results are as below
    However, these results are not making sense to me. I don't understand what different sections mean in the model. Would somebody, kindly, assist in interpreting these result.
    The command I used is:
    Code:
     local i = 25
     while `i' <= 100 {
    oaxaca_rif Productivity Age Agesq HH_type pltszbn seed_color Profit Improved_Var Bean_training, by(Gender_fm) wgt(0) rif(q(`i')) rwlogit(Productivity Age Agesq HH_type pltszbn seed_color Profit Improved_Var Bean_training)
    local i = `i'+25 
    }
    Estimating Reweighted RIF-OAXACA using RIF:q(25)
    Model : Blinder-Oaxaca RIF-decomposition
    Type : Reweighted
    RIF : q(25)
    Scale : 1
    Group 1: Gender_fm = 1 N of obs 1 = 267
    Group c: X2~>rw~>X1 N of obs C = 270
    Group 2: Gender_fm = 2 N of obs 2 = 270
    Productivity Coef. Std. Err. z P>z [95% Conf. Interval]
    Overall
    Group_1 281.5924 23.41396 12.03 0.000 235.7019 327.483
    Group_c 271.1421 25.16653 10.77 0.000 221.8166 320.4676
    Group_2 255.3442 23.71971 10.77 0.000 208.8544 301.834
    Tdifference 26.24825 33.32924 0.79 0.431 -39.07586 91.57236
    ToT_Explained 15.79795 6.325625 2.50 0.013 3.399955 28.19595
    ToT_Unexplained 10.4503 34.44848 0.30 0.762 -57.06748 77.96807
    Explained
    Total 15.79795 6.325625 2.50 0.013 3.399955 28.19595
    Pure_explained 4.724502 6.583372 0.72 0.473 -8.17867 17.62767
    Specif_err 11.07345 1.981957 5.59 0.000 7.188884 14.95801
    Pure_explained
    Age 6.637126 10.05447 0.66 0.509 -13.06928 26.34353
    Agesq -5.725608 9.090363 -0.63 0.529 -23.54239 12.09118
    HH_type -.6092167 1.15703 -0.53 0.599 -2.876954 1.658521
    pltszbn -11.11264 5.648631 -1.97 0.049 -22.18375 -.0415253
    seed_color 2.403569 3.027502 0.79 0.427 -3.530227 8.337365
    Profit 10.72668 4.543071 2.36 0.018 1.822427 19.63094
    Improved_Var 2.533347 2.172133 1.17 0.243 -1.723956 6.790649
    Bean_training -.1287579 .6357514 -0.20 0.840 -1.374808 1.117292
    Specif_err
    Age -65.72744 123.0801 -0.53 0.593 -306.96 175.5051
    Agesq 32.4753 59.85907 0.54 0.587 -84.84631 149.7969
    HH_type -5.034687 4.997181 -1.01 0.314 -14.82898 4.759608
    pltszbn 4.683856 6.128411 0.76 0.445 -7.32761 16.69532
    seed_color 13.45737 6.856492 1.96 0.050 .0188907 26.89585
    Profit -5.969148 3.920042 -1.52 0.128 -13.65229 1.713993
    Improved_Var 2.297751 2.858454 0.80 0.421 -3.304715 7.900217
    Bean_training -.1615344 .6396438 -0.25 0.801 -1.415213 1.092144
    _cons 35.05198 63.96981 0.55 0.584 -90.32655 160.4305
    Unexplained
    Total 10.4503 34.44848 0.30 0.762 -57.06748 77.96807
    Reweight_err -8.06465 22.60838 -0.36 0.721 -52.37627 36.24697
    Pure_Unexplained 18.51495 30.88905 0.60 0.549 -42.02648 79.05638
    Pure_Unexplained
    Age 84.516 650.2778 0.13 0.897 -1190.005 1359.037
    Agesq -33.10879 318.5419 -0.10 0.917 -657.4394 591.2218
    HH_type -12.45945 36.0617 -0.35 0.730 -83.13909 58.22019
    pltszbn 130.8818 41.06826 3.19 0.001 50.38949 211.3741
    seed_color 76.59187 48.11181 1.59 0.111 -17.70554 170.8893
    Profit -53.47701 18.50214 -2.89 0.004 -89.74055 -17.21347
    Improved_Var -23.15794 20.32391 -1.14 0.255 -62.99208 16.6762
    Bean_training -11.19626 9.179775 -1.22 0.223 -29.18828 6.795772
    _cons -140.0753 354.8483 -0.39 0.693 -835.5652 555.4147
    Reweight_err
    Age -1.551658 10.58733 -0.15 0.883 -22.30245 19.19914
    Agesq 1.99791 10.26672 0.19 0.846 -18.12448 22.1203
    HH_type -.0934782 .5721813 -0.16 0.870 -1.214933 1.027976
    pltszbn -10.75718 24.56547 -0.44 0.661 -58.90461 37.39024
    seed_color .1866233 2.090271 0.09 0.929 -3.910232 4.283479
    Profit 1.847514 8.674623 0.21 0.831 -15.15443 18.84946
    Improved_Var .007511 2.520041 0.00 0.998 -4.931678 4.9467
    Bean_training .2981116 4.244746 0.07 0.944 -8.021439 8.617662

  • #2
    Would someone help on this please?

    Comment


    • #3
      hi Co Ar
      As I mentioned before, the results suggest that there are differences in productivity across gender, but most of it is explained by specification errors.
      Im concerned that you have a relatively small sample, and that your data may not be fit for RIF-regression analysis if the distribution of the dependent variable is not continuous.
      HTH

      Comment

      Working...
      X