Graphics Reference
In-Depth Information
graph dot tenure, over(occ7)
over(collgrad)
Here, we use a second
over()
option to
show the mean of work experience
broken down by occupation and
whether one graduated college.
Uses nlsw.dta & scheme vg s1c
Prof
Mgmt
Sales
not college grad
Cler.
Operat.
Labor
Other
Prof
Mgmt
Sales
college grad
Cler.
Operat.
Labor
Other
0
2
4
6
8
mean of tenure
graph dot tenure, over(occ7) over(collgrad)
over(married)
We can add a third
over()
option, in
this case further breaking the
tenure
down by whether one is married. Note
that the first
over()
variable (
occ7
)is
now treated as multiple
not college grad
single
college grad
-variables.
When you use three
over()
options,
the first variable is then treated as
multiple
y
not college grad
married
college grad
-variables, as though you had
specified the
asyvars
option. This
graph can be dicult to read with
occ7
forming the multiple
y
0
2
4
6
8
10
mean of tenure
Prof
Mgmt
Sales
Cler.
-variables.
Uses nlsw.dta & scheme vg s1c
y
Operat.
Labor
Other
graph dot tenure,
over(married)
over(occ7) over(collgrad)
This graph shows the same data as the
last one, except we have switched the
order of the
over()
options, making
over(married)
come first and thus
forming the multiple
Prof
Mgmt
Sales
not college grad
Cler.
Operat.
Labor
-variables. This
might be easier to read than the
previous graph.
Uses nlsw.dta & scheme vg s1c
y
Other
Prof
Mgmt
Sales
college grad
Cler.
Operat.
Labor
Other
0
2
4
6
8
10
mean of tenure
single
married
The electronic form of this topic is solely for direct use at UCLA and only by faculty, students, and staff of UCLA.