---------------------------------------------------------------------------------------------------------

       log:  C:\AAA Miker Files\newer web pages\soc_388_notes\soc_388_2007\fifth_class_log.log

  log type:  text

 opened on:   9 Oct 2007, 11:03:30

 

. set linesize 75

 

. use "C:\AAA Miker Files\newer web pages\soc_388_notes\soc_388_2007\ed_intermar.dta", clear

 

. *I am going to press forward a bit with model fitting to the educational intermarriage 4x4 dataset.

. * I am going to be referring to models as they are numbered in my comprehensive excel file, which has most of the summary statistics from each model.

. *just for review

. desmat: poisson count hed wed

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                         -113882.425

   LR chi square:                                                                           215237.595

   Model degrees of freedom:                                                                         6

   Pseudo R-squared:                                                                             0.486

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            1.072**     0.004

2      Some Col                                                                      0.595**     0.005

3      BA+                                                                           0.235**     0.005

     wed

4      HS                                                                            1.229**     0.004

5      Some Col                                                                      0.733**     0.005

6      BA+                                                                           0.142**     0.005

7    _cons                                                                           9.187**     0.005

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  227578.9

         Prob > chi2(9)        =    0.0000

 

. *skipping ahead to M4, full endogamy:

. desmat: poisson count hed wed ed_endog_full

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                          -24059.274

   LR chi square:                                                                           394883.898

   Model degrees of freedom:                                                                        10

   Pseudo R-squared:                                                                             0.891

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            1.134**     0.007

2      Some Col                                                                      0.819**     0.006

3      BA+                                                                          -0.017*      0.007

     wed

4      HS                                                                            1.372**     0.007

5      Some Col                                                                      1.020**     0.007

6      BA+                                                                          -0.278**     0.008

     ed_endog_full

7      1                                                                             1.722**     0.009

8      2                                                                             0.676**     0.007

9      3                                                                             0.537**     0.008

10     4                                                                             2.487**     0.009

11   _cons                                                                           8.652**     0.008

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  47932.55

         Prob > chi2(5)        =    0.0000

 

. *One way to ask whether educational endogamy really matters, is to ask whether this model with 4 terms for the endogamy diagonal fits MUCH better than the independence model.

. *That would give us a chisquare test with 4 df, on the difference in goodness of fit between the models.

. display chi2tail(4,(227500-47000))

0

 

. *OK, so the P value for this comparison is Zero. What does that mean substantively?

. * P value of zero in that last test means we can reject the null hypothesis that the independence model fits as well as the full endogamy model, M4. On the other hand, the P=0 from poisgof means that M4 which we just ran still has a long way to go to fit the data well.

. *Let's add a few things, as we did last class, and then push it further.

. table hed wed, contents (mean  ed_endog_full)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        1         0         0         0

       HS |        0         2         0         0

 Some Col |        0         0         3         0

      BA+ |        0         0         0         4

--------------------------------------------------

 

. table hed wed, contents (mean   ed_diff_3)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        0         0         0         1

       HS |        0         0         0         0

 Some Col |        0         0         0         0

      BA+ |        1         0         0         0

--------------------------------------------------

 

. desmat: poisson count hed wed ed_endog_full  ed_diff_3

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                          -17940.195

   LR chi square:                                                                           407122.056

   Model degrees of freedom:                                                                        11

   Pseudo R-squared:                                                                             0.919

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            0.942**     0.007

2      Some Col                                                                      0.667**     0.007

3      BA+                                                                           0.009       0.007

     wed

4      HS                                                                            1.132**     0.007

5      Some Col                                                                      0.815**     0.007

6      BA+                                                                          -0.276**     0.008

     ed_endog_full

7      1                                                                             1.410**     0.010

8      2                                                                             0.796**     0.007

9      3                                                                             0.583**     0.007

10     4                                                                             2.147**     0.010

     ed_diff_3

11     1                                                                            -1.947**     0.023

12   _cons                                                                           8.964**     0.008

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  35694.39

         Prob > chi2(4)        =    0.0000

 

. *on one additional degree of freedom, we improved goodness of fit by about 12,000, which is good, but we still have a ways to go.

. *That was M5

. *now let's add a few terms.

. gen byte ed_diff_2=0

 

. replace  ed_diff_2=1 if (hed-wed==2) | (wed-hed==2)

(4 real changes made)

 

. table hed wed, contents (mean ed_diff_2)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        0         0         1         0

       HS |        0         0         0         1

 Some Col |        1         0         0         0

      BA+ |        0         1         0         0

--------------------------------------------------

 

. desmat: poisson count hed wed ed_endog_full  ed_diff_3 ed_diff_2

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                            -145.628

   LR chi square:                                                                           442711.189

   Model degrees of freedom:                                                                        12

   Pseudo R-squared:                                                                             0.999

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            0.627**     0.008

2      Some Col                                                                      0.355**     0.007

3      BA+                                                                           0.180**     0.008

     wed

4      HS                                                                            0.817**     0.008

5      Some Col                                                                      0.461**     0.007

6      BA+                                                                          -0.142**     0.009

     ed_endog_full

7      1                                                                             0.763**     0.011

8      2                                                                             0.779**     0.007

9      3                                                                             0.601**     0.008

10     4                                                                             1.195**     0.011

     ed_diff_3

11     1                                                                            -2.749**     0.024

     ed_diff_2

12     1                                                                            -1.068**     0.006

13   _cons                                                                           9.611**     0.009

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  105.2568

         Prob > chi2(3)        =    0.0000

 

. *first of all, notice that all of a sudden we have a poisgof test that actually comes into range.

. display chi2tail(3, 105)

1.307e-22

 

. *That's a small P value, meaning we still have some work to do, but on the other hand we're getting a lot closer. Then again, we only have 3 residual df to work with, so getting closer is in a sense not surprising. If we used all 16 terms available to us, we could fit the data exactly.

. *What do you make of the fact that the ed_endogamy terms are all positive, whereas the ed_diff terms are all negative so far?

. *The coefficients mean that compared to some (for the moment vague) comparison group, the probability or the odds of being married to someone with the same educational level as you is higher, and the odds of being married to someone with 2 or 3 categories difference from you is lower than we would otherwise expect.

.

. *Think about the actual data and predicted values of our various models.

. predict P_M6

(option n assumed; predicted number of events)

 

. *Those are the predicted values of model M6

. *let's go back and see how poorly the independence model and M4 fit the data.

. table hed wed, contents(sum  P_independence sum  P_independence) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS | 9773.551  33398.43  20349.32   11263.7     74785

          | 9773.551  33398.43  20349.32   11263.7     74785

          |

       HS |  28552.2  97569.33  59447.98   32905.5    218475

          |  28552.2  97569.33  59447.98   32905.5    218475

          |

 Some Col | 17727.26  60578.06  36909.58   20430.1    135645

          | 17727.26  60578.06  36909.58   20430.1    135645

          |

      BA+ | 12367.98  42264.19  25751.13   14253.7     94637

          | 12367.98  42264.19  25751.13   14253.7     94637

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

------------------------------------------------------------

 

. table hed wed, contents(sum  count sum  P_independence) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS |    32016     33374      8407       988     74785

          | 9773.551  33398.43  20349.32   11263.7     74785

          |

       HS |    28370    137876     43783      8446    218475

          |  28552.2  97569.33  59447.98   32905.5    218475

          |

 Some Col |     7051     48766     61633     18195    135645

          | 17727.26  60578.06  36909.58   20430.1    135645

          |

      BA+ |      984     13794     28635     51224     94637

          | 12367.98  42264.19  25751.13   14253.7     94637

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

------------------------------------------------------------

 

. *The independence model has way too few marriages along the endogamy diagonal, and way to many at the opposite corners.

. *independence does no justice to the data.

. table hed wed, contents(sum  count sum   P_endogamy_full) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS |    32016     33374      8407       988     74785

          |    32016  22561.17  15875.39  4332.443     74785

          |

       HS |    28370    137876     43783      8446    218475

          | 17790.29    137876  49342.89  13465.83    218475

          |

 Some Col |     7051     48766     61633     18195    135645

          |  12987.8  51193.47     61633   9830.73    135645

          |

      BA+ |      984     13794     28635     51224     94637

          | 5626.913  22179.36  15606.73     51224     94637

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

------------------------------------------------------------

 

. *now let's take a look at M6, the model we just ran, with terms for ed_diff 3 and ed_diff_2

. table hed wed, contents(sum  count sum   P_M6) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS |    32016     33374      8407       988     74785

          |    32016  33801.72  8138.919  828.3573     74785

          |

       HS |    28370    137876     43783      8446    218475

          | 27942.28    137876  44327.54  8329.189    218475

          |

 Some Col |     7051     48766     61633     18195    135645

          | 7319.081  48221.46     61633  18471.45    135645

          |

      BA+ |      984     13794     28635     51224     94637

          | 1143.643  13910.81  28358.55     51224     94637

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

------------------------------------------------------------

 

. *M6 was the first model whose poisgof was in the neighborhood, chisquare test of 105 on 3 df.

. *There does seem to be a little bit of a gender disparity in the far corners of the model, where M6 overpredicts the number of <HS educated women married to BA+ men, and underpredicts the number of <HS men married to BA+ women.

. *I'm going to follow the excel table for a minute, and add a term for M7 which has husbands one level higher than wives...

. gen byte ed_diff1_male=0

 

. replace  ed_diff1_male=1 if hed-wed==1

(3 real changes made)

 

. table hed wed, contents( mean ed_diff1_male)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        0         0         0         0

       HS |        1         0         0         0

 Some Col |        0         1         0         0

      BA+ |        0         0         1         0

--------------------------------------------------

 

. desmat: poisson count hed wed ed_endog_full  ed_diff_3 ed_diff_2 ed_diff1_male

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                            -110.210

   LR chi square:                                                                           442782.026

   Model degrees of freedom:                                                                        13

   Pseudo R-squared:                                                                             1.000

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            0.614**     0.008

2      Some Col                                                                      0.320**     0.008

3      BA+                                                                           0.136**     0.009

     wed

4      HS                                                                            0.841**     0.008

5      Some Col                                                                      0.494**     0.008

6      BA+                                                                          -0.093**     0.010

     ed_endog_full

7      1                                                                             0.796**     0.011

8      2                                                                             0.801**     0.008

9      3                                                                             0.637**     0.009

10     4                                                                             1.223**     0.011

     ed_diff_3

11     1                                                                            -2.713**     0.024

     ed_diff_2

12     1                                                                            -1.036**     0.007

     ed_diff1_male

13     1                                                                             0.057**     0.007

14   _cons                                                                           9.578**     0.010

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  34.42006

         Prob > chi2(2)        =    0.0000

 

. predict M7

(option n assumed; predicted number of events)

 

. *let's take a quick look at residuals from M7

. rename M7 P_M7

 

. *for consistency

. gen M7_residuals= P_M7-count

 

. table hed wed, contents (sum count sum  P_M7 sum M7_residuals) row col

 

-----------------------------------------------------------------

husband's |                   wife's education                   

education |       <HS         HS   Some Col        BA+      Total

----------+------------------------------------------------------

      <HS |     32016      33374       8407        988      74785

          |     32016   33497.12   8398.321   873.5618      74785

          |         0   123.1172  -8.678711  -114.4382   .0002441

          |

       HS |     28370     137876      43783       8446     218475

          |  28246.88     137876   43725.78   8626.337     218475

          | -123.1172          0  -57.21875   180.3369   .0009766

          |

 Some Col |      7051      48766      61633      18195     135645

          |  7059.679   48823.22      61633    18129.1     135645

          |  8.679199   57.21875          0  -65.89844  -.0004883

          |

      BA+ |       984      13794      28635      51224      94637

          |  1098.438   13613.66    28700.9      51224      94637

          |  114.4382  -180.3369   65.89844          0  -.0002441

          |

    Total |     68421     233810     142458      78853     523542

          |     68421     233810     142458      78853     523542

          |  .0002441  -.0009766   .0009766   .0002441   .0004883

-----------------------------------------------------------------

 

. *Where does M7 seem not quite to fit?

. display chi2tail(2, 34)

4.140e-08

 

. *There are several cells that have a difference in the neighborhood of 100 or so. How can we tell which cells are most important?

. *key is to standardize by taking into account the magnitude of what the predicted value in each cell is.

. poisgof

 

         Goodness-of-fit chi2  =  34.42006

         Prob > chi2(2)        =    0.0000

 

. poisgof, pearson

 

         Goodness-of-fit chi2  =  34.61454

         Prob > chi2(2)        =    0.0000

 

. *The pearson chisquare is going to be especially useful to us, you will see why

. gen M7_resid_pearson= M7_residuals/( P_M7^.5)

 

. table hed wed, contents (sum count sum  P_M7 sum  M7_resid_pearson) row col

 

-----------------------------------------------------------------

husband's |                   wife's education                  

education |       <HS         HS   Some Col        BA+      Total

----------+------------------------------------------------------

      <HS |     32016      33374       8407        988      74785

          |     32016   33497.12   8398.321   873.5618      74785

          |         0     .67269   -.094702  -3.871902  -3.293914

          |

       HS |     28370     137876      43783       8446     218475

          |  28246.88     137876   43725.78   8626.337     218475

          | -.7325435          0  -.2736337   1.941652    .935475

          |

 Some Col |      7051      48766      61633      18195     135645

          |  7059.679   48823.22      61633    18129.1     135645

          |  .1032969   .2589555          0  -.4894259  -.1271735

          |

      BA+ |       984      13794      28635      51224      94637

          |  1098.438   13613.66    28700.9      51224      94637

          |  3.452895    -1.5456   .3889801          0   2.296275

          |

    Total |     68421     233810     142458      78853     523542

          |     68421     233810     142458      78853     523542

          |  2.823648  -.6139546   .0206444  -2.419675  -.1893376

-----------------------------------------------------------------

 

. *The cells with the larger pearson residuals (in absolute value) are the cells where our model seems to fit the worst.

. *The two cells with the most unequal educational attainments are the cells with the largest (in absolute value) pearson residuals.

. *Another way of looking at pearson residuals, is to square them and then add them.

. gen M7_pearson_resid_squared= M7_resid_pearson^2

 

. table hed wed, contents (sum count sum  P_M7 sum   M7_pearson_resid_squared) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS |    32016     33374      8407       988     74785

          |    32016  33497.12  8398.321  873.5618     74785

          |        0  .4525118  .0089685  14.99162   15.4531

          |

       HS |    28370    137876     43783      8446    218475

          | 28246.88    137876  43725.78  8626.337    218475

          |   .53662         0  .0748754  3.770013  4.381509

          |

 Some Col |     7051     48766     61633     18195    135645

          | 7059.679  48823.22     61633   18129.1    135645

          | .0106702   .067058         0  .2395377  .3172659

          |

      BA+ |      984     13794     28635     51224     94637

          | 1098.438  13613.66   28700.9     51224     94637

          | 11.92248   2.38888  .1513055         0  14.46267

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

          | 12.46977  2.908449  .2351494  19.00117  34.61454

------------------------------------------------------------

 

. *The sum over all cells of the pearson residual squared is simply the pearson chisquare statistic, 34.61454 for this model.

. *We had one term for ed_diff_3 to fit these two cells. We need to add a second term to account for the gender disparity

. gen byte ed_diff_3_male=0

 

. replace ed_diff_3_male=1 if hed-wed==3

(1 real change made)

 

. table hed wed, contents(mean ed_diff_3_male)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        0         0         0         0

       HS |        0         0         0         0

 Some Col |        0         0         0         0

      BA+ |        1         0         0         0

--------------------------------------------------

 

. *Once we add this second ed_diff_3 term, we will be fitting those two cells of most unequal education

>  exactly.

. desmat: poisson count hed wed ed_endog_full  ed_diff_3 ed_diff_2 ed_diff1_male ed_diff_3_male

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                             -95.087

   LR chi square:                                                                           442812.272

   Model degrees of freedom:                                                                        14

   Pseudo R-squared:                                                                             1.000

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            0.618**     0.008

2      Some Col                                                                      0.330**     0.008

3      BA+                                                                           0.150**     0.010

     wed

4      HS                                                                            0.833**     0.008

5      Some Col                                                                      0.484**     0.008

6      BA+                                                                          -0.110**     0.011

     ed_endog_full

7      1                                                                             0.789**     0.011

8      2                                                                             0.798**     0.008

9      3                                                                             0.631**     0.009

10     4                                                                             1.220**     0.011

     ed_diff_3

11     1                                                                            -2.579**     0.033

     ed_diff_2

12     1                                                                            -1.042**     0.007

     ed_diff1_male

13     1                                                                             0.047**     0.007

     ed_diff_3_male

14     1                                                                            -0.264**     0.048

15   _cons                                                                           9.585**     0.010

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  4.174479

         Prob > chi2(1)        =    0.0410

 

. *check it out. This model actually fits reasonably well.

. *We are using 15 out of 16 terms, so maybe we should not congratulate ourselves too much, but still..

 

. predict P_M8

(option n assumed; predicted number of events)

 

. table hed wed, contents(sum count sum  P_M8) row col

 

------------------------------------------------------------

husband's |                 wife's education               

education |      <HS        HS  Some Col       BA+     Total

----------+-------------------------------------------------

      <HS |    32016     33374      8407       988     74785

          |    32016  33457.31  8323.688       988     74785

          |

       HS |    28370    137876     43783      8446    218475

          | 28286.69    137876     43783  8529.313    218475

          |

 Some Col |     7051     48766     61633     18195    135645

          | 7134.312     48766     61633  18111.69    135645

          |

      BA+ |      984     13794     28635     51224     94637

          |      984  13710.69  28718.31     51224     94637

          |

    Total |    68421    233810    142458     78853    523542

          |    68421    233810    142458     78853    523542

------------------------------------------------------------

 

. *One last point:

. *In M8, the ed endogamy terms 1 and 2 seem awfully close. Could we save 1 df by combining them?

. test _x_7-_x_8=0

 

 ( 1)  [count]_x_7 - [count]_x_8 = 0

 

           chi2(  1) =    0.30

         Prob > chi2 =    0.5821

 

. *these things are pretty close- can't reject the null of no difference.

 

. gen byte ed_diff_full_revised= ed_endog_full

 

. replace  ed_diff_full_revised=1 if  ed_endog_full==2

(1 real change made)

 

. table hed wed, contents (mean ed_diff_full_revised)

 

--------------------------------------------------

husband's |            wife's education          

education |      <HS        HS  Some Col       BA+

----------+---------------------------------------

      <HS |        1         0         0         0

       HS |        0         1         0         0

 Some Col |        0         0         3         0

      BA+ |        0         0         0         4

--------------------------------------------------

 

. *The actual numbers don't matter, because stata desmat or xi will generate dummy variables for every different level, but here we have 3 different levels of ed endogamy rather than 4.

. *how does it fit?

. desmat: poisson count hed wed  ed_diff_full_revised  ed_diff_3 ed_diff_2 ed_diff1_male ed_diff_3_male

-------------------------------------------------------------------------------------------------------

   Poisson regression

-------------------------------------------------------------------------------------------------------

   Dependent variable                                                                            count

   Optimization:                                                                                    ml

   Number of observations:                                                                          16

   Initial log likelihood:                                                                 -221501.223

   Log likelihood:                                                                             -95.239

   LR chi square:                                                                           442811.969

   Model degrees of freedom:                                                                        13

   Pseudo R-squared:                                                                             1.000

   Prob:                                                                                         0.000

-------------------------------------------------------------------------------------------------------

nr Effect                                                                            Coeff        s.e.

-------------------------------------------------------------------------------------------------------

   count

     hed

1      HS                                                                            0.622**     0.005

2      Some Col                                                                      0.331**     0.008

3      BA+                                                                           0.151**     0.009

     wed

4      HS                                                                            0.837**     0.005

5      Some Col                                                                      0.486**     0.007

6      BA+                                                                          -0.108**     0.010

     ed_diff_full_revised

7      1                                                                             0.795**     0.006

8      3                                                                             0.632**     0.009

9      4                                                                             1.220**     0.011

     ed_diff_3

10     1                                                                            -2.577**     0.033

     ed_diff_2

11     1                                                                            -1.041**     0.007

     ed_diff1_male

12     1                                                                             0.047**     0.007

     ed_diff_3_male

13     1                                                                            -0.263**     0.048

14   _cons                                                                           9.580**     0.006

-------------------------------------------------------------------------------------------------------

*  p < .05

** p < .01

 

. poisgof

 

         Goodness-of-fit chi2  =  4.477238

         Prob > chi2(2)        =    0.1066

 

. *That's model 9, fit very nicely.

. save "C:\AAA Miker Files\newer web pages\soc_388_notes\soc_388_2007\ed_intermar.dta", replace

file C:\AAA Miker Files\newer web pages\soc_388_notes\soc_388_2007\ed_intermar.dta saved

 

. exit, clear