Stata Technical Bulletin
29
. regress job fem phd ment fel art cit
|
Source I |
SS |
df |
MS |
Number of obs = 408 T? / Л ЛЛП — *7 70 | ||
|
— |
1 ∖ Vt *±V ɪ √ |
— -L I . I Q | ||||
|
Model I |
81.0584763 |
6 13. |
5097461 |
Prob > F |
= 0.0000 | |
|
Residual ∣ |
304.737915 |
401 .759944926 |
R-Squared |
= 0.2101 | ||
|
Adj R-Squared |
= 0.1983 | |||||
|
— | ||||||
|
Total I |
385.796392 |
407 .947902683 |
Root MSE |
= .87175 | ||
|
— job I |
Coef. |
Std. Err. |
t |
p>∣t∣ |
[957. Conf. |
— Interval] |
|
---------+- |
— | |||||
|
fem I |
-.1391939 |
.0902344 |
-1.543 |
0.124 |
-.3165856 |
.0381977 |
|
phd I |
.2726826 |
.0493183 |
5.529 |
0.000 |
.1757278 |
.3696375 |
|
ment I |
.0011867 |
.0007012 |
1.692 |
0.091 |
-.0001917 |
.0025651 |
|
fel I |
.2341384 |
.0948206 |
2.469 |
0.014 |
.0477308 |
.4205461 |
|
art I |
.0228011 |
.0288843 |
0.789 |
0.430 |
-.0339824 |
.0795846 |
|
cit I |
.0044788 |
.0019687 |
2.275 |
0.023 |
.0006087 |
.008349 |
|
_cons I |
1.067184 |
.1661357 |
6.424 |
0.000 |
.7405785 |
1.39379 |
Iistcoef provides additional information:
. Iistcoef, help std constant
regress (N=408): Unstandardized and Standardized Estimates
Observed SD: .97360294
SD of Error: .8717482
|
job I |
b |
t |
p>∣t∣ |
bStdX |
bStdY |
bStdXY |
SDofX |
|
— | |||||||
|
fem I |
-0.13919 |
-1.543 |
0.124 |
-0.0680 |
-0.1430 |
-0.0698 |
0.4883 |
|
phd I |
0.27268 |
5.529 |
0.000 |
0.2601 |
0.2801 |
0.2671 |
0.9538 |
|
ment I |
0.00119 |
1.692 |
0.091 |
0.0778 |
0.0012 |
0.0799 |
65.5299 |
|
fel I |
0.23414 |
2.469 |
0.014 |
0.1139 |
0.2405 |
0.1170 |
0.4866 |
|
art I |
0.02280 |
0.789 |
0.430 |
0.0514 |
0.0234 |
0.0528 |
2.2561 |
|
cit I |
0.00448 |
2.275 |
0.023 |
0.1481 |
0.0046 |
0.1521 |
33.0599 |
|
„cons I |
1.06718 |
6.424 |
0.000 | ||||
|
— b = |
raw coefficient |
— | |||||
|
t = |
t-score for |
test of |
b=0 | ||||
|
p>∣t∣ = |
p-value for |
t-test | |||||
bStdX = х-standardized coefficient
bStdY = у-standardized coefficient
bStdXY = fully standardized coefficient
SDofX = standard deviation of X
Example with logit
The logit model illustrates that Iistcoef can be used to obtain alternative transformations of the basic parameters. We
begin by estimating the logit model, which produces the standard output:
|
. logit Ifp k5 k618 age we he Iwg inct nolog Logit estimates Log likelihood = -452.63296 |
Number of obs = Prob > chi2 = Pseudo R2 = |
753 | ||||
|
— Ifp I |
Coef. |
Std. Err. |
z |
P>∣z∣ |
[957. Conf. |
— Interval] |
|
— | ||||||
|
кБ I |
-1.462913 |
. 1970006 |
-7.426 |
0.000 |
-1.849027 |
-1.076799 |
|
k618 I |
-.0645707 |
.0680008 |
-0.950 |
0.342 |
-.1978499 |
.0687085 |
|
age I |
-.0628706 |
.0127831 |
-4.918 |
0.000 |
-.0879249 |
-.0378162 |
|
wc I |
.8072738 |
.2299799 |
3.510 |
0.000 |
.3565215 |
1.258026 |
|
he I |
.1117336 |
.2060397 |
0.542 |
0.588 |
-.2920969 |
.515564 |
|
Iwg I |
.6046931 |
.1508176 |
4.009 |
0.000 |
.3090961 |
.9002901 |
|
inc I |
-.0344464 |
.0082084 |
-4.196 |
0.000 |
-.0505346 |
-.0183583 |
|
_cons I |
3.18214 |
.6443751 |
4.938 |
0.000 |
1.919188 |
4.445092 |
Most frequently, the logit model is interpreted using factor change coefficients, also known as odds ratios. These are the default
option for Iistcoef.
. Iistcoef, help