Welcome to the Institute for Digital Reseach and Education
Institute for Digital Reseach and Education Home
Help the Stat Consulting Group by giving a gift
Stata Textbook Examples
Regression Analysis by Example, Third Edition
Chapter 2: Simple Linear Regression
Table 2.3, page 25.
use http://www.ats.ucla.edu/stat/stata/examples/chp/p025a, clear
list
y x
1. 1 -7
2. 14 -6
3. 25 -5
4. 34 -4
5. 41 -3
6. 46 -2
7. 49 -1
8. 50 0
9. 49 1
10. 46 2
11. 41 3
12. 34 4
13. 25 5
14. 14 6
15. 1 7
Figure 2.2, page 25.
graph twoway scatter y x, xlabel(-4 0 4)
Part of table 2.4, page 25.
use http://www.ats.ucla.edu/stat/stata/examples/chp/p025b, clear
list y1 x1
y1 x1
1. 8.04 10
2. 6.95 8
3. 7.58 13
4. 8.81 9
5. 8.33 11
6. 9.96 14
7. 7.24 6
8. 4.26 4
9. 10.84 12
10. 4.82 7
11. 5.68 5
Figure 2.3(a), page 26.
graph twoway (scatter y1 x1) (lfit y1 x1)
Part of table 2.4, page 25.
list y2 x2
y2 x2
1. 9.14 10
2. 8.14 8
3. 8.74 13
4. 8.77 9
5. 9.26 11
6. 8.1 14
7. 6.13 6
8. 3.1 4
9. 9.13 12
10. 7.26 7
11. 4.74 5
Figure 2.3(b), page 26.
graph twoway (scatter y2 x2) (lfit y2 x2)
Part of table 2.4, page 25.
list y3 x3
y3 x3
1. 7.46 10
2. 6.77 8
3. 12.74 13
4. 7.11 9
5. 7.81 11
6. 8.84 14
7. 6.08 6
8. 5.39 4
9. 8.15 12
10. 6.42 7
11. 5.73 5
Figure 2.3(c), page 26.
graph twoway (scatter y3 x3) (lfit y3 x3)
Part of table 2.4, page 25.
list y4 x4
y4 x4
1. 6.58 8
2. 5.76 8
3. 7.71 8
4. 8.84 8
5. 8.47 8
6. 7.04 8
7. 5.25 8
8. 12.5 19
9. 5.56 8
10. 7.91 8
11. 6.89 8
Figure 2.3(d), page 26.
graph twoway (scatter y4 x4) (lfit y4 x4)
Part of table 2.6, page 28.
use http://www.ats.ucla.edu/stat/stata/examples/chp/p027, clear
list
minutes units
1. 23 1
2. 29 2
3. 49 3
4. 64 4
5. 74 4
6. 87 5
7. 96 6
8. 97 6
9. 109 7
10. 119 8
11. 149 9
12. 145 9
13. 154 10
14. 166 10
Commands to create remainder of table 2.6, page 28.
egen ymean = mean(minutes) /* egen is extended generate to create a new variable */ egen xmean = mean(units) generate ydev = minutes - ymean /* generate creates new variables */ generate xdev = units - xmean drop ymean xmean /* drop ymean and xmean, they are no longer needed */ generate ydev2 = ydev^2 generate xdev2 = xdev^2 generate yxdev = ydev*xdev
List remainder of table 2.6, page 28.
list ydev-yxdev
ydev xdev ydev2 xdev2 yxdev yhat
1. -74.21429 -5 5507.76 25 371.0714 19.67043
2. -68.21429 -4 4653.189 16 272.8571 35.1792
3. -48.21429 -3 2324.617 9 144.6429 50.68797
4. -33.21429 -2 1103.189 4 66.42857 66.19674
5. -23.21429 -2 538.9031 4 46.42857 66.19674
6. -10.21429 -1 104.3317 1 10.21429 81.70551
7. -1.214287 0 1.474492 0 0 97.21429
8. -.2142868 0 .0459188 0 0 97.21429
9. 11.78571 1 138.903 1 11.78571 112.7231
10. 21.78571 2 474.6173 4 43.57143 128.2318
11. 51.78571 3 2681.76 9 155.3571 143.7406
12. 47.78571 3 2283.474 9 143.3571 143.7406
13. 56.78571 4 3224.617 16 227.1429 159.2494
14. 68.78571 4 4731.474 16 275.1429 159.2494
Figure 2.4, page 28.
graph twoway scatter minutes units, ylabel(40(40)160)
Table 2.9, page 36.
regress minutes units Source | SS df MS Number of obs = 14 ---------+------------------------------ F( 1, 12) = 943.20 Model | 27419.5088 1 27419.5088 Prob > F = 0.0000 Residual | 348.848371 12 29.0706976 R-squared = 0.9874 ---------+------------------------------ Adj R-squared = 0.9864 Total | 27768.3571 13 2136.02747 Root MSE = 5.3917 ------------------------------------------------------------------------------ minutes | Coef. Std. Err. t P>|t| [95% Conf. Interval] ---------+-------------------------------------------------------------------- units | 15.50877 .5049813 30.712 0.000 14.40851 16.60903 _cons | 4.161654 3.3551 1.240 0.239 -3.148482 11.47179 ------------------------------------------------------------------------------
Commands to produce table 2.7, page 32.
predict yhat /* default for predict produces predicted (fitted) scores */ predict e, resid /* resid option produces raw residuals */
Table 2.7, page 32.
list units yhat e
units yhat e
1. 1 19.67043 3.329574
2. 2 35.1792 -6.179198
3. 3 50.68797 -1.68797
4. 4 66.19674 -2.196742
5. 4 66.19674 7.803258
6. 5 81.70551 5.294486
7. 6 97.21429 -1.214286
8. 6 97.21429 -.2142857
9. 7 112.7231 -3.723058
10. 8 128.2318 -9.23183
11. 9 143.7406 5.259398
12. 9 143.7406 1.259398
13. 10 159.2494 -5.249373
14. 10 159.2494 6.750627
Figure 2.5, page 32.
graph twoway (scatter minutes units) (lfit minutes units), ylabel(40(40)160)
The confidence interval on page 38 included in table 2.9 above.
Standard error for a predicted score, page 39.
predict seyhat, stdf
list seyhat
seyhat
1. 6.125547
2. 5.935257
3. 5.782926
4. 5.671614
5. 5.671614
6. 5.603765
7. 5.580966
8. 5.580966
9. 5.603765
10. 5.671614
11. 5.782926
12. 5.782926
13. 5.935257
14. 5.935257
Standard error for mean prediction, page 39.
predict semu, stdp
list semu
minutes units semu
1. 23 1 2.907169
2. 29 2 2.481245
3. 49 3 2.090821
4. 64 4 1.759688
5. 74 4 1.759688
6. 87 5 1.52692
7. 96 6 1.440999
8. 97 6 1.440999
9. 109 7 1.52692
10. 119 8 1.759688
11. 149 9 2.090821
12. 145 9 2.090821
13. 154 10 2.481245
14. 166 10 2.481245
Correlations, page 43.
correlat minutes units
(obs=14)
| minutes units
---------+------------------
minutes | 1.0000
units | 0.9937 1.0000
correlate minutes yhat
(obs=14)
| minutes yhat
---------+------------------
minutes | 1.0000
yhat | 0.9937 1.0000
Correlation squared, page 43.
Note: The display command demonstrates Stata's ability to function as a calculator.
display .9937^2 .98743969
R-squared from regression sums of squares, page 43.
Note: This display uses values e(rss) and e(mss) saved by the regression command. It will work only after the regression has been estimated.
display 1 - (e(rss)/(e(rss)+e(mss))) .9874372
Save the modified data file p027.
save p027, replace
The content of this web site should not be construed as an endorsement of any particular web site, book, or software product by the University of California.