SPSS Cheat Sheet
SPSS Cheat Sheet
to
Story
Project:
SPSS
Cheat
Sheet
for
Analyzing
General
Social
Survey
Data
This
guide
is
intended
to
help
you
explore
and
analyze
the
variables
you
have
selected
for
your
group
project.
To compute frequencies for the gender, race, and occupational variables, [SEX, RACE, INDUS80] follow these steps:
1. Click
Analyze,
click
Descriptive
Statistics,
and
then
click
Frequencies.
When
you
do
this,
you
will
see
the
Frequencies
dialog
box
as
shown
below.
2. Holding
down
the
Ctrl
key,
click
INDUS80,
SEX,
and
RACE
to
select
them,
then
click
►to
place
them
in
the
Variable(s)
box.
3. Click
Statistics.
You
will
see
the
Frequencies:
Statistics
dialog
box
as
shown
below
4. Under
the
Central
Tendency
area,
click
Mode.
5. Click
Continue.
INLS
200
Retrieving
&
Analyzing
Information
Spring
2014
Page
1
6. Click
OK.
The
output
for
the
analysis
is
shown
in
part
below.
The
output
initially
presents
the
mode
for
each
of
the
three
variables.
The
tables
labeled
RS
INDUSTRY
CODE,
RESPONDENTS
SEX,
RACE
OF
RESPONDENT
show
the
frequencies
(counts)
for
these
variables.
In
addition,
the
tables
show
the
percentage
of
participants
in
each
category.
Because
the
variables
are
qualitative,
the
column
labeled
Cumulative
Percent
is
not
meaningful.
Bar
charts
are
often
used
to
display
the
results
of
categorical
or
qualitative
variables.
Bar
charts
allow
for
the
visual
representation
of
the
frequencies
in
each
category
and
can
be
used
to
display
results
of
variables
with
a
relatively
large
number
of
categories.
An
alternative
to
the
bar
chart
is
the
pie
chart.
Pie
charts
also
present
the
frequencies
or
percentages
in
each
category
but
in
a
form
that
can
be
edited
to
highlight
specific
categories.
Pie
charts
are
more
useful
for
displaying
results
of
variables
that
have
relatively
few
categories,
if
there
are
more
than
a
few,
pie
charts
become
cluttered
and
difficult
to
read
if
variables
have
many
categories.
For
example
the
RS
INDUSTRY
CODE
has
over
100
categories
–
way
too
many
for
a
pie
chart.
To create a pie chart for the RACE variable, follow these steps:
To
edit
the
pie
chart:
1. Double-‐click
on
the
chart
to
select
it
for
editing
2. Click
on
Elements
and
click
on
Show
Data
Labels.
You
should
now
see
the
Properties
dialog
box.
3. Click
on
the
Data
Value
Labels
tab
of
the
Properties
box
if
not
currently
selected.
4. Click
on
RACE
in
the
Labels
Not
Displayed
area
and
then
click
on
the
green
upward
pointing
arrow
to
move
RACE
Status
to
the
Labels
Displayed
area.
5. Click
Apply
in
the
Properties
dialog
box.
You
should
now
see
appropriate
labels
in
the
slices
of
the
pie
chart.
6. Click
on
the
Text
Style
tab
of
the
Properties
dialog
box.
7. In
the
front
area,
click
on
the
Size
drop-‐down
menu
and
choose
a
font
size
(e.g.
10).
8. Click
Apply
in
the
Properties
dialog
box.
The
labels
should
now
have
a
larger
font
size.
9. Click
Close
in
the
Properties
dialog
box.
10. Click
on
Options
from
the
main
menu.
Click
on
Hide
Legend.
The
graph
should
look
like
this:
You
may
want
to
select
only
some
of
the
“cases”
in
the
data
set.
For
example
you
may
want
to
look
only
at
females,
or
only
respondents
who
live
in
a
certain
region
of
the
country
or
only
respondents
who
identify
themselves
as
‘extremely
conservative’.
Before
you
begin
to
analyze
the
data,
you
will
want
to
select
cases
that
meet
your
criteria.
1. First
you
need
to
look
at
the
response
options
for
the
variable
you
are
interested
in
limiting.
For
example,
look
at
the
Variable
view
of
the
data
set
and
find
a
particular
variable
–
HAPPY
[General
Happiness].
In
the
Value
column
you
may
click
on
the
possible
values/options
that
were
provided
to
the
respondent.
In
this
case
each
respondent
would
chose
Not
Applicable,
Very
Happy,
Pretty
Happy,
Not
too
Happy,
Don’t
Know,
or
Didn’t
Answer.
Each
of
these
choices
is
assigned
a
numeric
value
[0,
1,
2,
3,
8,
or
9].
2. Click
Data
-‐-‐
Select
Cases
3. There
are
a
number
of
choices.
A
random
sample
of
cases,
a
sample
based
on
a
range,
a
filter
variable,
or
a
condition
can
be
used
to
select
cases.
For
this
example,
“If
condition
is
satisfied”
will
be
used.
Click
on
“If
condition
is
satisfied”
Then
click
“If…”
5. Click
Continue.
6. In
terms
of
Output,
there
are
several
options.
The
selected
cases
could
be
copied
into
a
new
dataset,
deleted,
or
filtered
out.
In
this
instance,
the
unselected
cases
will
be
filtered
out.
Click
OK.
7. In
the
DATA
VIEW,
note
the
slashes
through
many
of
the
cases.
These
cases
were
respondents
who
selected
any
other
choice
than
Very
Happy.
Cases
2,
4,
and
10
have
a
general
happiness
coding
of
1
for
Very
Happy
and
remain
in
the
sample.
All
analyses
done
with
the
cases
selected
will
only
include
Very
Happy
respondents.