You want to put in your regression a variable that takes the value 1 for for
one gender (e.g. female) and 0 for the other gender.
In order to create this variable you have to find out how your data are
coded. Sometimes they are already coded as you would like, sometimes not.
To find out how they are coded you can use
. codebook gender
You will get something like this
----------------------------------------------------------------------------
----------------------------------------
gender
respondents sex
----------------------------------------------------------------------------
----------------------------------------
type: numeric (byte)
label: sex
range: [1,2] units: 1
unique values: 2 missing .: 0/7028
tabulation: Freq. Numeric Label
4080 1 male
2948 2 female
This example tells you that male correponds to 1 and female to 2, it also
tells me that there are no observations in which the value for gender has
not been recorded. Sometimes the datasets are not labeled and you can't tell
which is which by using -codebook-; in this case you have to use the
physical codebook of your dataset.
In order to create the variable that we need, the easiest syntax for
beginner is
. generate female=1 if gender==2
. replace female=0 if gender==1
Now you can use female as your regressor.
. regress mfm1 female
Best,
Renzo
----------------------------------------------------------------------------
----
*From Syed O Masood <[email protected]>
To [email protected]
Subject st: Interpreting Regression
Date Sun, 22 Aug 2004 14:54:58 -0700 (PDT)
----------------------------------------------------------------------------
----
I have to interpret the effect of gender on blood
flow.
I have copied the result from stata.
Source | SS df MS
Number of obs = 79
-------------+------------------------------
F( 1, 77) = 5.34
Model | 52.8286516 1 52.8286516
Prob > F = 0.0235
Residual | 761.23203 77 9.88613026
R-squared = 0.0649
-------------+------------------------------
Adj R-squared = 0.0528
Total | 814.060681 78 10.4366754
Root MSE = 3.1442
----------------------------------------------------------------------------
--
mfm1 | Coef. Std. Err. t P>|t|
[95% Conf. Interval]
-------------+--------------------------------------------------------------
--
gender | -1.674738 .7244781 -2.31 0.023
-3.117358 -.2321178
_cons | 9.453125 .4538293 20.83 0.000
8.549435 10.35681
----------------------------------------------------------------------------
--
How do I interpret which sex (gender) ?Male or ?Female
is explains the decrease in blood flow. Gender
accounts for 6% of variability in blood flow.
Please advice.
*
* For searches and help try:
* http://www.stata.com/support/faqs/res/findit.html
* http://www.stata.com/support/statalist/faq
* http://www.ats.ucla.edu/stat/stata/
