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

      name:  <unnamed>

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

> roj3\fall_2010_s381_logs\class14.log

  log type:  text

 opened on:   9 Nov 2010, 12:03:35

 

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

 

 

 

. regress incwage male age age_sq lawyers if  occ1990==178|occ1990==125

 

      Source |       SS       df       MS              Number of obs =     447

-------------+------------------------------           F(  4,   442) =    5.96

       Model |  1.0759e+11     4  2.6898e+10           Prob > F      =  0.0001

    Residual |  1.9958e+12   442  4.5153e+09           R-squared     =  0.0512

-------------+------------------------------           Adj R-squared =  0.0426

       Total |  2.1034e+12   446  4.7160e+09           Root MSE      =   67196

 

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

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

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

        male |   17090.75   7088.051     2.41   0.016     3160.276    31021.22

         age |    5026.88   1434.899     3.50   0.001     2206.808    7846.953

      age_sq |  -46.29393   14.42811    -3.21   0.001    -74.65014   -17.93771

     lawyers |   36634.82   27921.33     1.31   0.190    -18240.23    91509.88

       _cons |  -99244.38   45668.63    -2.17   0.030      -188999   -9489.743

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

 

 

. jacknife: regress incwage male age age_sq lawyers if  occ1990==178|occ1990==125

(running regress on estimation sample)

 

Jackknife replications (447)

----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5

..................................................    50

..................................................   100

..................................................   150

..................................................   200

..................................................   250

..................................................   300

..................................................   350

..................................................   400

...............................................

 

Linear regression                               Number of obs      =       447

                                                Replications       =       447

                                                F(   4,    446)    =     10.48

                                                Prob > F           =    0.0000

                                                R-squared          =    0.0512

                                                Adj R-squared      =    0.0426

                                                Root MSE           =  6.72e+04

 

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

             |              Jackknife

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

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

        male |   17090.75   5845.159     2.92   0.004     5603.271    28578.22

         age |    5026.88   1112.785     4.52   0.000     2839.927    7213.834

      age_sq |  -46.29393   11.50344    -4.02   0.000     -68.9016   -23.68625

     lawyers |   36634.82   7824.133     4.68   0.000     21258.08    52011.57

       _cons |  -99244.38   29046.14    -3.42   0.001    -156328.7   -42160.09

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

 

. regress incwage male age age_sq lawyers if  occ1990==178|occ1990==125, robust

 

Linear regression                                      Number of obs =     447

                                                       F(  4,   442) =   11.49

                                                       Prob > F      =  0.0000

                                                       R-squared     =  0.0512

                                                       Root MSE      =   67196

 

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

             |               Robust

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

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

        male |   17090.75       5835     2.93   0.004     5622.954    28558.54

         age |    5026.88   1098.171     4.58   0.000     2868.595    7185.165

      age_sq |  -46.29393   11.30526    -4.09   0.000    -68.51267   -24.07518

     lawyers |   36634.82    7021.79     5.22   0.000     22834.58    50435.07

       _cons |  -99244.38   28613.76    -3.47   0.001    -155480.3   -43008.45

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

 

. jackknife: regress incwage male age age_sq lawyers if  occ1990==178|occ1990==125

(running regress on estimation sample)

 

Jackknife replications (447)

----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5

..................................................    50

..................................................   100

..................................................   150

..................................................   200

..................................................   250

..................................................   300

..................................................   350

..................................................   400

...............................................

 

Linear regression                               Number of obs      =       447

                                                Replications       =       447

                                                F(   4,    446)    =     10.48

                                                Prob > F           =    0.0000

                                                R-squared          =    0.0512

                                                Adj R-squared      =    0.0426

                                                Root MSE           =  6.72e+04

 

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

             |              Jackknife

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

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

        male |   17090.75   5845.159     2.92   0.004     5603.271    28578.22

         age |    5026.88   1112.785     4.52   0.000     2839.927    7213.834

      age_sq |  -46.29393   11.50344    -4.02   0.000     -68.9016   -23.68625

     lawyers |   36634.82   7824.133     4.68   0.000     21258.08    52011.57

       _cons |  -99244.38   29046.14    -3.42   0.001    -156328.7   -42160.09

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

 

. regress incwage male age age_sq lawyers if  occ1990==178|occ1990==125, vce(jackknife)

(running regress on estimation sample)

 

Jackknife replications (447)

----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5

..................................................    50

..................................................   100

..................................................   150

..................................................   200

..................................................   250

..................................................   300

..................................................   350

..................................................   400

...............................................

 

Linear regression                               Number of obs      =       447

                                                Replications       =       447

                                                F(   4,    446)    =     10.48

                                                Prob > F           =    0.0000

                                                R-squared          =    0.0512

                                                Adj R-squared      =    0.0426

                                                Root MSE           =  6.72e+04

 

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

             |              Jackknife

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

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

        male |   17090.75   5845.159     2.92   0.004     5603.271    28578.22

         age |    5026.88   1112.785     4.52   0.000     2839.927    7213.834

      age_sq |  -46.29393   11.50344    -4.02   0.000     -68.9016   -23.68625

     lawyers |   36634.82   7824.133     4.68   0.000     21258.08    52011.57

       _cons |  -99244.38   29046.14    -3.42   0.001    -156328.7   -42160.09

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

 

*class started here…

 

. ttest incwage if occ1990==178|oc1990==125, by (occ1990)

oc1990 not found

r(111);

 

. ttest incwage if occ1990==178|occ1990==125, by (occ1990)

 

Two-sample t test with equal variances

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

   Group |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. Interval]

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

Sociolog |       6    41508.33    2842.722    6963.219    34200.88    48815.78

 Lawyers |     441    74044.33    3287.284    69032.96     67583.6    80505.06

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

combined |     447     73607.6    3248.139    68673.38    67224.04    79991.16

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

    diff |           -32535.99    28215.44               -87988.05    22916.07

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

    diff = mean(Sociolog) - mean(Lawyers)                         t =  -1.1531

Ho: diff = 0                                     degrees of freedom =      445

 

    Ha: diff < 0                 Ha: diff != 0                 Ha: diff > 0

 Pr(T < t) = 0.1247         Pr(|T| > |t|) = 0.2495          Pr(T > t) = 0.8753

 

. ttest incwage if occ1990==178|occ1990==125, by (occ1990) unequal

 

Two-sample t test with unequal variances

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

   Group |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. Interval]

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

Sociolog |       6    41508.33    2842.722    6963.219    34200.88    48815.78

 Lawyers |     441    74044.33    3287.284    69032.96     67583.6    80505.06

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

combined |     447     73607.6    3248.139    68673.38    67224.04    79991.16

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

    diff |           -32535.99    4345.953               -41456.75   -23615.24

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

    diff = mean(Sociolog) - mean(Lawyers)                         t =  -7.4865

Ho: diff = 0                     Satterthwaite's degrees of freedom =  26.7692

 

    Ha: diff < 0                 Ha: diff != 0                 Ha: diff > 0

 Pr(T < t) = 0.0000         Pr(|T| > |t|) = 0.0000          Pr(T > t) = 1.0000

 

* If you will recall HW2, there was a big difference between equal variance and unequal variance t-tests as far as the lawyer-sociologist difference was concerned.

 

. ttest incwage if occ1990==178|occ1990==125, by (occ1990)

 

Two-sample t test with equal variances

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

   Group |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. Interval]

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

Sociolog |       6    41508.33    2842.722    6963.219    34200.88    48815.78

 Lawyers |     441    74044.33    3287.284    69032.96     67583.6    80505.06

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

combined |     447     73607.6    3248.139    68673.38    67224.04    79991.16

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

    diff |           -32535.99    28215.44               -87988.05    22916.07

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

    diff = mean(Sociolog) - mean(Lawyers)                         t =  -1.1531

Ho: diff = 0                                     degrees of freedom =      445

 

    Ha: diff < 0                 Ha: diff != 0                 Ha: diff > 0

 Pr(T < t) = 0.1247         Pr(|T| > |t|) = 0.2495          Pr(T > t) = 0.8753

 

. ttest incwage if occ1990==178|occ1990==125, by (occ1990) unequal

 

Two-sample t test with unequal variances

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

   Group |     Obs        Mean    Std. Err.   Std. Dev.   [95% Conf. Interval]

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

Sociolog |       6    41508.33    2842.722    6963.219    34200.88    48815.78

 Lawyers |     441    74044.33    3287.284    69032.96     67583.6    80505.06

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

combined |     447     73607.6    3248.139    68673.38    67224.04    79991.16

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

    diff |           -32535.99    4345.953               -41456.75   -23615.24

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

    diff = mean(Sociolog) - mean(Lawyers)                         t =  -7.4865

Ho: diff = 0                     Satterthwaite's degrees of freedom =  26.7692

 

    Ha: diff < 0                 Ha: diff != 0                 Ha: diff > 0

 Pr(T < t) = 0.0000         Pr(|T| > |t|) = 0.0000          Pr(T > t) = 1.0000

 

. regress incwage age age_sq lawyers if  occ1990==178|occ1990==125

 

      Source |       SS       df       MS              Number of obs =     447

-------------+------------------------------           F(  3,   443) =    5.94

       Model |  8.1342e+10     3  2.7114e+10           Prob > F      =  0.0006

    Residual |  2.0220e+12   443  4.5644e+09           R-squared     =  0.0387

-------------+------------------------------           Adj R-squared =  0.0322

       Total |  2.1034e+12   446  4.7160e+09           Root MSE      =   67560

 

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

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

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

         age |   5192.546   1441.019     3.60   0.000     2360.463     8024.63

      age_sq |   -46.5991   14.50573    -3.21   0.001    -75.10769   -18.09051

     lawyers |   43885.33   27909.35     1.57   0.117    -10965.85     98736.5

       _cons |    -101263   45908.38    -2.21   0.028    -191488.2   -11037.71

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

 

* Regress gives us the equal variance t-test (here slightly different because we have added some additional controls).

 

. jackknife: regress incwage age age_sq lawyers if  occ1990==178|occ1990==125

(running regress on estimation sample)

 

Jackknife replications (447)

----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5

..................................................    50

..................................................   100

..................................................   150

..................................................   200

..................................................   250

..................................................   300

..................................................   350

..................................................   400

...............................................

 

Linear regression                               Number of obs      =       447

                                                Replications       =       447

                                                F(   3,    446)    =     17.49

                                                Prob > F           =    0.0000

                                                R-squared          =    0.0387

                                                Adj R-squared      =    0.0322

                                                Root MSE           =  6.76e+04

 

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

             |              Jackknife

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

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

         age |   5192.546   1121.748     4.63   0.000     2987.978    7397.114

      age_sq |   -46.5991   11.50142    -4.05   0.000     -69.2028    -23.9954

     lawyers |   43885.33   6164.988     7.12   0.000     31769.29    56001.36

       _cons |    -101263   28817.54    -3.51   0.000      -157898   -44627.94

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

 

* The jackknife runs the same regression N times, dropping one point each time. The coefficients are unchanged, but the standard errors of the coefficients are just the standard deviation of the N trials for each beta. The bigger the N, the more time this process will take.

 

. regress incwage age age_sq lawyers if  occ1990==178|occ1990==125

 

      Source |       SS       df       MS              Number of obs =     447

-------------+------------------------------           F(  3,   443) =    5.94

       Model |  8.1342e+10     3  2.7114e+10           Prob > F      =  0.0006

    Residual |  2.0220e+12   443  4.5644e+09           R-squared     =  0.0387

-------------+------------------------------           Adj R-squared =  0.0322

       Total |  2.1034e+12   446  4.7160e+09           Root MSE      =   67560

 

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

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

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

         age |   5192.546   1441.019     3.60   0.000     2360.463     8024.63

      age_sq |   -46.5991   14.50573    -3.21   0.001    -75.10769   -18.09051

     lawyers |   43885.33   27909.35     1.57   0.117    -10965.85     98736.5

       _cons |    -101263   45908.38    -2.21   0.028    -191488.2   -11037.71

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

 

. regress incwage age age_sq lawyers if  occ1990==178|occ1990==125,vce(jackknife)

(running regress on estimation sample)

 

Jackknife replications (447)

----+--- 1 ---+--- 2 ---+--- 3 ---+--- 4 ---+--- 5

..................................................    50

..................................................   100

..................................................   150

..................................................   200

..........................................--Break--

r(1);

 

* The above is just another syntax for the same jackknife request, so I interrupted it rather than wait for the output.

 

. regress incwage age age_sq lawyers if  occ1990==178|occ1990==125,vce(robust)

 

Linear regression                                      Number of obs =     447

                                                       F(  3,   443) =   19.63

                                                       Prob > F      =  0.0000

                                                       R-squared     =  0.0387

                                                       Root MSE      =   67560

 

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

             |               Robust

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

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

         age |   5192.546   1107.785     4.69   0.000      3015.38    7369.713

      age_sq |   -46.5991   11.30753    -4.12   0.000    -68.82216   -24.37604

     lawyers |   43885.33   5794.468     7.57   0.000     32497.27    55273.39

       _cons |    -101263   28523.55    -3.55   0.000    -157321.3   -45204.69

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

 

* Robust regression is a one-step alteration of the standard errors which is described in detail in the Stata manual, and which in this case yields results similar to the jackknife, and similar to the unequal variance regression which most students thought was preferable to the equal variance assumption in this case…

 

. log close

      name:  <unnamed>

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

> c_meth_proj3\fall_2010_s381_logs\class14.log

  log type:  text

 closed on:   9 Nov 2010, 16:00:38

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