-----------------------------------------------------------------------------------
log: C:\AAA Miker Files\newer web pages\soc_meth_proj3\class9_2009.log
log type: text
opened on: 24 Feb 2009, 11:29:47
. set mem 200m
Current memory allocation
current memory usage
settable value description (1M = 1024k)
--------------------------------------------------------------------
set maxvar 5000 max. variables allowed 1.909M
set memory 200M max. data space 200.000M
set matsize 400 max. RHS vars in models 1.254M
-----------
203.163M
. use "C:\AAA Miker Files\newer web pages\soc_meth_proj3\cps_mar_2000_new.dta", clear
*running through some regressions with dummy variables, interactions and our familiar three occupations
. gen new_occ=occ1990
r(199);
. replace new_occ=. if occ1990~=178 & occ1990~=125& occ1990~=95
(132297 real changes made, 132297 to missing)
. tabulate new_occ
new_occ | Freq. Percent Cum.
------------+-----------------------------------
95 | 966 68.37 68.37
125 | 6 0.42 68.79
178 | 441 31.21 100.00
------------+-----------------------------------
Total | 1,413 100.00
*Note the interaction asterisk in between new_occ and sex, below. This asks xi to produce all the possible combinations of interactions between the two variables.
. xi: regress incwage i.new_occ*i.sex
i.new_occ _Inew_occ_95-178 (naturally coded; _Inew_occ_95 omitted)
i.sex _Isex_1-2 (naturally coded; _Isex_1 omitted)
i.new~c*i.sex _InewXsex_#_# (coded as above)
Source | SS df MS Number of obs = 1413
-------------+------------------------------ F( 5, 1407) = 50.58
Model | 4.5116e+11 5 9.0232e+10 Prob > F = 0.0000
Residual | 2.5101e+12 1407 1.7840e+09 R-squared = 0.1524
-------------+------------------------------ Adj R-squared = 0.1493
Total | 2.9612e+12 1412 2.0972e+09 Root MSE = 42237
------------------------------------------------------------------------------
incwage | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
_Inew_oc~125 | -9402.452 30344.26 -0.31 0.757 -68927.32 50122.41
_Inew_oc~178 | 31633.97 5879.32 5.38 0.000 20100.79 43167.15
_Isex_2 | -11824.52 5545.056 -2.13 0.033 -22701.99 -947.0565
_InewXse~5_2 | 15287.02 36996.59 0.41 0.680 -57287.39 87861.44
_InewXse~8_2 | -8707.162 7067.771 -1.23 0.218 -22571.67 5157.342
_cons | 48602.45 5364.158 9.06 0.000 38079.84 59125.06
------------------------------------------------------------------------------
. predict M_class9_interactions
(option xb assumed; fitted values)
(132297 missing values generated)
. table new_occ sex, contents(mean incwage mean M_class9_interactions)
------------------------------------
| Sex
new_occ | Male Female
----------+-------------------------
95 | 48602.45161 36777.9281
| 48602.45 36777.93
|
125 | 39200 42662.5
| 39200 42662.5
|
178 | 80236.42208 59704.73684
| 80236.42 59704.74
------------------------------------
. *part of the reason I don't like xi so much is that the resulting table is hard to read. But you can see above that with 6 terms the predicted and actual values coincide on these 6 cells.
. label define new_occ_lbl 95 "nurses" 125 "soc" 178 "lawyers"
. label val new_occ new_occ_lbl
. desmat: regress incwage new_occ*sex
---------------------------------------------------------------------------------
Linear regression
---------------------------------------------------------------------------------
Dependent variable incwage
Number of observations: 1413
F statistic: 50.578
Model degrees of freedom: 5
Residual degrees of freedom: 1407
R-squared: 0.152
Adjusted R-squared: 0.149
Root MSE 42237.424
Prob: 0.000
---------------------------------------------------------------------------------
nr Effect Coeff s.e.
---------------------------------------------------------------------------------
new_occ
1 soc -9402.452 30344.261
2 lawyers 31633.970** 5879.320
sex
3 Female -11824.524* 5545.056
new_occ.sex
4 soc.Female 15287.024 36996.590
5 lawyers.Female -8707.162 7067.771
6 _cons 48602.452** 5364.158
---------------------------------------------------------------------------------
* p < .05
** p < .01
. predict M_class9_interactions_again
(option xb assumed; fitted values)
(132297 missing values generated)
* The same as previous, but this time with desmat... And now on to anscombe’s data.
. save "C:\AAA Miker Files\newer web pages\soc_meth_proj3\cps_mar_2000_new.dta",
> replace
file C:\AAA Miker Files\newer web pages\soc_meth_proj3\cps_mar_2000_new.dta saved
. clear
. edit
(8 vars, 11 obs pasted into editor)
- preserve
. regress y2 x2
Source | SS df MS Number of obs = 11
-------------+------------------------------ F( 1, 9) = 17.97
Model | 27.5000024 1 27.5000024 Prob > F = 0.0022
Residual | 13.776294 9 1.53069933 R-squared = 0.6662
-------------+------------------------------ Adj R-squared = 0.6292
Total | 41.2762964 10 4.12762964 Root MSE = 1.2372
------------------------------------------------------------------------------
y2 | Coef. Std. Err. t P>|t| [95% Conf. Interval]
-------------+----------------------------------------------------------------
x2 | .5 .1179638 4.24 0.002 .2331475 .7668526
_cons | 3.000909 1.125303 2.67 0.026 .4552978 5.54652
------------------------------------------------------------------------------
. twoway (scatter y2 x2) (lfit y2 x2)
. *This is the stata version of the scatter plot of y2 on x2, with the linear fit(from a simple linear regression) superimposed
. exit, clear