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

      name:  <unnamed>

       log:  C:\Documents and Settings\Michael Rosenfeld\My Documents\newer web pages\soc_meth_proj3\2010_logs\section_four.log

  log type:  text

 opened on:  16 Feb 2010, 12:15:02

 

. use "C:\Documents and Settings\Michael Rosenfeld\Desktop\cps_mar_2000_new.dta", clear

 

. regress incwage female

 

      Source |       SS       df       MS              Number of obs =  103226

-------------+------------------------------           F(  1,103224) = 5006.28

       Model |  3.9723e+12     1  3.9723e+12           Prob > F      =  0.0000

    Residual |  8.1905e+13103224   793465967           R-squared     =  0.0463

-------------+------------------------------           Adj R-squared =  0.0462

       Total |  8.5877e+13103225   831940347           Root MSE      =   28169

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |  -12418.63   175.5159   -70.76   0.000    -12762.64   -12074.63

       _cons |    25943.8   126.7965   204.61   0.000     25695.28    26192.32

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

 

. regress incwage female  Korean_vet

 

      Source |       SS       df       MS              Number of obs =   92865

-------------+------------------------------           F(  2, 92862) = 2711.18

       Model |  4.0347e+12     2  2.0173e+12           Prob > F      =  0.0000

    Residual |  6.9097e+13 92862   744082727           R-squared     =  0.0552

-------------+------------------------------           Adj R-squared =  0.0551

       Total |  7.3132e+13 92864   787514009           Root MSE      =   27278

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |  -13172.95   183.1608   -71.92   0.000    -13531.94   -12813.96

  Korean_vet |  -17929.45     672.63   -26.66   0.000     -19247.8   -16611.11

       _cons |   26628.72   140.0058   190.20   0.000     26354.31    26903.13

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

 

. regress incwage female  Korean_vet [aweight= perwt_rounded]

(sum of wgt is   1.9224e+08)

 

      Source |       SS       df       MS              Number of obs =   92865

-------------+------------------------------           F(  2, 92862) = 2705.82

       Model |  4.2126e+12     2  2.1063e+12           Prob > F      =  0.0000

    Residual |  7.2286e+13 92862   778428329           R-squared     =  0.0551

-------------+------------------------------           Adj R-squared =  0.0550

       Total |  7.6499e+13 92864   823774386           Root MSE      =   27900

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |  -13439.69   187.0091   -71.87   0.000    -13806.23   -13073.16

  Korean_vet |  -18314.59   695.6556   -26.33   0.000    -19678.07   -16951.11

       _cons |   27284.84   142.3742   191.64   0.000     27005.79     27563.9

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

 

. *regress assumes all the predictor variables are continuous, and you use i.variable to indicate otherwise. desmat reverses that assumption, and assumes that all the predictors are categorical, and you use @ to indicate continuous variables.

 

. display -13439/187

-71.86631

 

. *get used to seeing the t statistic as beta divided by its standard error

 

. regress incwage female  Korean_vet i.metro [aweight= perwt_rounded]

(sum of wgt is   1.9224e+08)

 

      Source |       SS       df       MS              Number of obs =   92865

-------------+------------------------------           F(  6, 92858) = 1101.29

       Model |  5.0820e+12     6  8.4700e+11           Prob > F      =  0.0000

    Residual |  7.1417e+13 92858   769098857           R-squared     =  0.0664

-------------+------------------------------           Adj R-squared =  0.0664

       Total |  7.6499e+13 92864   823774386           Root MSE      =   27733

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |  -13379.51   185.9099   -71.97   0.000    -13743.89   -13015.12

  Korean_vet |  -17933.67   691.8545   -25.92   0.000    -19289.69   -16577.64

             |

       metro |

          1  |  -8232.328   1892.845    -4.35   0.000    -11942.29   -4522.371

          2  |  -3490.151   1890.107    -1.85   0.065    -7194.742    214.4387

          3  |  -47.68832   1886.323    -0.03   0.980    -3744.861    3649.485

          4  |  -4783.277    1897.19    -2.52   0.012     -8501.75   -1064.805

             |

       _cons |   30322.75   1884.631    16.09   0.000     26628.89     34016.6

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

 

. *now let me do the same regression with desmat

 

. desmat: regress incwage female  Korean_vet metro [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                           1101.289

   Model degrees of freedom:                                                     6

   Residual degrees of freedom:                                              92858

   R-squared:                                                                0.066

   Adjusted R-squared:                                                       0.066

   Root MSE                                                              27732.632

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -13379.506**   185.910

   Korean_vet

2    1                                                      -17933.665**   691.854

   metro

3    Not in metro area                                       -8232.328**  1892.845

4    Central city                                            -3490.151    1890.107

5    Outside central city                                      -47.688    1886.323

6    Central city status unknown                             -4783.277*   1897.190

7  _cons                                                     30322.747**  1884.631

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

*  p < .05

** p < .01

 

 

 

* note the "@" in front of age in the below regression.

.

desmat: regress incwage female  Korean_vet metro @age [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                            946.636

   Model degrees of freedom:                                                     7

   Residual degrees of freedom:                                              92857

   R-squared:                                                                0.067

   Adjusted R-squared:                                                       0.067

   Root MSE                                                              27730.163

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -13514.761**   188.678

   Korean_vet

2    1                                                      -18581.637**   708.887

   metro

3    Not in metro area                                       -8236.839**  1892.677

4    Central city                                            -3442.369    1889.973

5    Outside central city                                      -24.318    1886.163

6    Central city status unknown                             -4759.511*   1897.030

7  Age                                                          21.869**     5.222

8  _cons                                                     29469.076**  1895.457

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

*  p < .05

** p < .01

 

. gen age_sq=age^2

*this is how we generate the age-squared variable. Notice on your variable list that it will be added to the bottom.

 

 

. desmat: regress incwage female  Korean_vet metro @age @age_sq [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                           2535.406

   Model degrees of freedom:                                                     8

   Residual degrees of freedom:                                              92856

   R-squared:                                                                0.179

   Adjusted R-squared:                                                       0.179

   Root MSE                                                              26002.864

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -12728.320**   177.063

   Korean_vet

2    1                                                      -14957.251**   665.505

   metro

3    Not in metro area                                       -6558.295**  1774.846

4    Central city                                            -2033.091    1772.292

5    Outside central city                                      828.436    1768.691

6    Central city status unknown                             -3276.152    1778.913

7  Age                                                        2494.205**    22.439

8  age_sq                                                      -26.561**     0.235

9  _cons                                                    -20601.844**  1831.883

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

*  p < .05

** p < .01

 

. *by adding the age-squared term, we improved the R-square from 6.7% to 17.9%, a really big improvement.

 

*The T-statistic is just the coefficient divided by its standard error, or, for age:

. display 2494/22.439

111.14577

 

. desmat: regress incwage female  Korean_vet metro @age_sq [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                            999.508

   Model degrees of freedom:                                                     7

   Residual degrees of freedom:                                              92857

   R-squared:                                                                0.070

   Adjusted R-squared:                                                       0.070

   Root MSE                                                              27678.724

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -12749.202**   188.474

   Korean_vet

2    1                                                      -14919.641**   708.397

   metro

3    Not in metro area                                       -8146.532**  1889.171

4    Central city                                            -3646.682    1886.451

5    Outside central city                                     -117.839    1882.660

6    Central city status unknown                             -4830.460*   1893.504

7  age_sq                                                       -1.041**     0.055

8  _cons                                                     32143.370**  1883.393

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

*  p < .05

** p < .01

 

. *leaving out age and including only age-squared (as we do above) is a bad idea, and pushes our r-square back to 7%. If we have age-square in the model, we should also have age.

 

. desrep, zval prob

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                            999.508

   Model degrees of freedom:                                                     7

   Residual degrees of freedom:                                              92857

   R-squared:                                                                0.070

   Adjusted R-squared:                                                       0.070

   Root MSE                                                              27678.724

   Prob:                                                                     0.000

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

nr Effect                                    Coeff        s.e.       t        prob

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

   female

1    1                                  -12749.202**   188.474   -67.644     0.000

   Korean_vet

2    1                                  -14919.641**   708.397   -21.061     0.000

   metro

3    Not in metro area                   -8146.532**  1889.171    -4.312     0.000

4    Central city                        -3646.682    1886.451    -1.933     0.053

5    Outside central city                 -117.839    1882.660    -0.063     0.950

6    Central city status unknown         -4830.460*   1893.504    -2.551     0.011

7  age_sq                                   -1.041**     0.055   -19.054     0.000

8  _cons                                 32143.370**  1883.393    17.067     0.000

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

*  p < .05

** p < .01

 

. *if you are using desmat, it is handy to also use desrep, which is installed automatically with desmat. After a regression, desmat will give you a regression output table and you can control what the output looks like. In this case we use desmat, zval prob to generate the output with the z or t statistics, and probability as well.

 

. regress incwage female  Korean_vet i.metro age age_sq [aweight= perwt_rounded]

(sum of wgt is   1.9224e+08)

 

      Source |       SS       df       MS              Number of obs =   92865

-------------+------------------------------           F(  8, 92856) = 2535.41

       Model |  1.3714e+13     8  1.7143e+12           Prob > F      =  0.0000

    Residual |  6.2784e+13 92856   676148962           R-squared     =  0.1793

-------------+------------------------------           Adj R-squared =  0.1792

       Total |  7.6499e+13 92864   823774386           Root MSE      =   26003

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |  -12728.32   177.0628   -71.89   0.000    -13075.36   -12381.28

  Korean_vet |  -14957.25   665.5054   -22.48   0.000    -16261.63   -13652.87

             |

       metro |

          1  |  -6558.295   1774.846    -3.70   0.000    -10036.97   -3079.617

          2  |  -2033.091   1772.292    -1.15   0.251    -5506.764    1440.582

          3  |   828.4365   1768.691     0.47   0.640     -2638.18    4295.053

          4  |  -3276.152   1778.913    -1.84   0.066    -6762.803    210.4993

             |

         age |   2494.205   22.43866   111.16   0.000     2450.225    2538.184

      age_sq |  -26.56104   .2352543  -112.90   0.000    -27.02213   -26.09994

       _cons |  -20601.84   1831.883   -11.25   0.000    -24192.31   -17011.37

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

 

. xi: regress incwage female  Korean_vet i.metro age_sq [aweight= perwt_rounded]

i.metro           _Imetro_0-4         (naturally coded; _Imetro_0 omitted)

(sum of wgt is   1.9224e+08)

 

      Source |       SS       df       MS              Number of obs =   92865

-------------+------------------------------           F(  7, 92857) =  999.51

       Model |  5.3601e+12     7  7.6573e+11           Prob > F      =  0.0000

    Residual |  7.1139e+13 92857   766111788           R-squared     =  0.0701

-------------+------------------------------           Adj R-squared =  0.0700

       Total |  7.6499e+13 92864   823774386           Root MSE      =   27679

 

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

     incwage |      Coef.   Std. Err.      t    P>|t|     [95% Conf. Interval]

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

      female |   -12749.2   188.4743   -67.64   0.000    -13118.61   -12379.79

  Korean_vet |  -14919.64   708.3965   -21.06   0.000    -16308.09   -13531.19

   _Imetro_1 |  -8146.532   1889.171    -4.31   0.000    -11849.29   -4443.776

   _Imetro_2 |  -3646.682   1886.451    -1.93   0.053    -7344.106    50.74231

   _Imetro_3 |  -117.8387    1882.66    -0.06   0.950    -3807.832    3572.155

   _Imetro_4 |   -4830.46   1893.504    -2.55   0.011    -8541.708   -1119.212

      age_sq |  -1.041315   .0546509   -19.05   0.000     -1.14843   -.9341998

       _cons |   32143.37   1883.393    17.07   0.000     28451.94     35834.8

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

 

. desmat: regress incwage female  Korean_vet metro @age @age_sq [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                   92865

   aweight:                                                          perwt_rounded

   F statistic:                                                           2535.406

   Model degrees of freedom:                                                     8

   Residual degrees of freedom:                                              92856

   R-squared:                                                                0.179

   Adjusted R-squared:                                                       0.179

   Root MSE                                                              26002.864

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -12728.320**   177.063

   Korean_vet

2    1                                                      -14957.251**   665.505

   metro

3    Not in metro area                                       -6558.295**  1774.846

4    Central city                                            -2033.091    1772.292

5    Outside central city                                      828.436    1768.691

6    Central city status unknown                             -3276.152    1778.913

7  Age                                                        2494.205**    22.439

8  age_sq                                                      -26.561**     0.235

9  _cons                                                    -20601.844**  1831.883

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

*  p < .05

** p < .01

 

. tabulate vetlast

 

     Veteran's most recent |

         period of service |      Freq.     Percent        Cum.

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

                       NIU |     30,904       23.11       23.11

                No service |     91,149       68.17       91.28

              World War II |      2,428        1.82       93.10

                Korean War |      1,716        1.28       94.38

               Vietnam Era |      3,683        2.75       97.14

             Other service |      3,830        2.86      100.00

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

                     Total |    133,710      100.00

 

. codebook vetlast

 

. codebook vetlast

 

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

vetlast                                     Veteran's most recent period of service

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

 

                  type:  numeric (byte)

                 label:  vetlastlbl

 

                 range:  [0,9]                        units:  1

         unique values:  6                        missing .:  0/133710

 

            tabulation:  Freq.   Numeric  Label

                         30904         0  NIU

                         91149         1  No service

                          2428         4  World War II

                          1716         6  Korean War

                          3683         8  Vietnam Era

                          3830         9  Other service

 

. gen korean_vet_new=0

 

. replace  korean_vet_new=1 if vetlast==6

(1716 real changes made)

 

. desmat: regress incwage female   korean_vet_new metro @age @age_sq [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                      incwage

   Number of observations:                                                  103226

   aweight:                                                          perwt_rounded

   F statistic:                                                           2837.895

   Model degrees of freedom:                                                     8

   Residual degrees of freedom:                                             103217

   R-squared:                                                                0.180

   Adjusted R-squared:                                                       0.180

   Root MSE                                                              26676.307

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -12476.602**   168.069

   korean_vet_new

2    1                                                      -14247.101**   674.085

   metro

3    Not in metro area                                       -4837.811**  1685.612

4    Central city                                             -191.578    1683.374

5    Outside central city                                     2793.861    1679.635

6    Central city status unknown                             -1278.184    1689.596

7  Age                                                        2560.560**    21.927

8  age_sq                                                      -27.464**     0.227

9  _cons                                                    -23534.293**  1745.882

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

*  p < .05

** p < .01

 

. desmat: regress inctot female korean_vet_new metro @age @age_sq [aweight= perwt_rounded]

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

   Linear regression

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

   Dependent variable                                                       inctot

   Number of observations:                                                  103226

   aweight:                                                          perwt_rounded

   F statistic:                                                           2545.734

   Model degrees of freedom:                                                     8

   Residual degrees of freedom:                                             103217

   R-squared:                                                                0.165

   Adjusted R-squared:                                                       0.165

   Root MSE                                                              29926.690

   Prob:                                                                     0.000

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

nr Effect                                                        Coeff        s.e.

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

   female

1    1                                                      -15702.652**   188.548

   korean_vet_new

2    1                                                       -4169.903**   756.219

   metro

3    Not in metro area                                       -6213.618**  1890.996

4    Central city                                            -1081.445    1888.486

5    Outside central city                                     2576.141    1884.291

6    Central city status unknown                             -1796.468    1895.465

7  Age                                                        2623.563**    24.599

8  age_sq                                                      -25.183**     0.254

9  _cons                                                    -22497.580**  1958.610

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

*  p < .05

** p < .01

 

. *the disadvantage of Korean war vets is much less in inctot than in incwage. I suspect this is because veterans get benefits

 

. * The key for this regression process is that instead of throwing out the women and the people who don't fall in the same age range as the Korean vets (as we did in HW1 when we were trying to compare vets to non-vets the same age), here we use regression to account for age and gender, and then see if there is any residual difference between Korean vets and non vets after controling for age and gender. And it turns out that there is. Korean vets actually make less than similarly

 

. log close

      name:  <unnamed>

       log:  C:\Documents and Settings\Michael Rosenfeld\My Documents\newer web pag

> es\soc_meth_proj3\2010_logs\section_four.log

  log type:  text

 closed on:  16 Feb 2010, 13:06:19

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