Organizing data in tables and charts: Criteria

Organizing data
in tables and charts:
Criteria for effective presentation
Jane E. Miller, Ph.D.
Rutgers University

About the author
Author: The Chicago Guide to Writing about
Multivariate Analysis (Chicago, 2005) and The
Chicago Guide to Writing about Numbers
(Chicago, 2004), and other articles about
statistical literacy and quantitative
communication.
Professor, Rutgers University
 Institute for Health, Health Care Policy and Aging
Research.
 Edward J. Bloustein School of Planning and Public
Policy.

Learning objectives
To learn the different types of variables
and how they affect choices for organizing
data.
To become aware of different principles
for organizing variables in tables or charts.
To learn the strengths and weaknesses of
tables, charts, and prose for organizing
and conveying numeric information.

Performance objectives
To be able to choose among different
criteria for organizing data for a particular
task.
To be able to identify whether to use a
table or chart to present data for a specific
objective.
To understand how to write a prose
description to coordinate with a table or
chart.

Why does order of variables matter?
The arrangement of items in a table or chart
should coordinate with order they are
mentioned in the prose description.
 Avoid zigzagging back and forth across a chart or
among rows and columns of a table.
Usually describe a pattern based on observed
numeric values, e.g., most to least common.
Often a hypothesis includes some theoretical
basis of how items relate to one another.

Ordinal and continuous variables
Values of ordinal, interval, and ratio variables
have an inherent numeric order.
 E.g., age groups, dates, blood pressure.
Numeric or chronological order of values is the
principle for organizing those values in a table
or chart.

Nominal variables
Values of nominal variables have no inherent
numeric order.
 E.g., categories of race, gender, or region.
Need an organizing principle to determine
sequence of items.
Same issue if you have >1 variable to present.
 Several different causes of death.
 Prevalence of >1 symptoms, attitudes, etc.

+ and - of different tools
Strengths Weaknesses
Prose  Easiest way to
explain patterns
 Hard to organize a
lot of numbers
Table  Holds lots of #s
 Good for detail
 Predictable
structure
 Harder to "see"
patterns
Chart  Holds lots of #s
 Easy to see
general patterns
 Predictable
structure
 Difficult to see
specific values

Complementary use of
prose, tables & charts
Use tables and charts to present full
set of numeric values.
Use prose to describe the pattern or
address the hypothesis.
Use same ordering principle in table
or chart and its accompanying prose.
Improves clarity of narrative line.

Prose description of a pattern
Objectives:
Describe size and shape of the pattern.
Explain whether it matches hypothesis.
Specify direction and magnitude of
association.
Direction: “Which is higher?
Magnitude: “How much higher?”

Direction for different types of variables
Direction for ordinal, interval or ratio
variable:
 Is the relationship positive, negative, or level?
 E.g., as income rises, do death rates
increase, decrease or remain constant?
For nominal variables:
 Which category has the highest value?
 E.g., which gender has the higher death rate?

Principles for organizing data
Alphabetical order
Order of items on original data
collection instrument
Empirical order
Theoretical groupings
Arbitrary order – NEVER a good idea!
Think about how the data will be used,
and choose one of the above principles!

For tables and charts
accompanied by prose
Pattern description
or hypothesis testing

Example: Attitudes about legal abortion
“Please tell me whether or not you think it
should be possible for a pregnant woman
to obtain a legal abortion”
% of
respondents
who agree
If the woman wants it for any reason 43.7
If there is a strong chance of defect in the baby 79.8
If the woman's own health is seriously
endangered by the pregnancy 88.2
If she is not married and does not want to marry
the man 42.5
If she becomes pregnant as a result of rape 80.8
If she is married and does not want any more
children 44.4
From the 2000 U.S. General Social Survey

Order of items from questionnaire
Agreement with legal abortion under specified circumstances,
2000 U.S. General Social Survey
0
20
40
60
80
100
Any
reason
Defect in
baby
Wants no
more kids
Mother's
health
Pregnant
due to
rape
Not
married
%
of
respondents

Alphabetical order
0
20
40
60
80
100
Any
reason
Defect in
baby
Mother's
health
Not
married
Rape Wants no
more
%
of
respondents

Empirical order (descending)
0
20
40
60
80
100
Mother's
health
Rape Defect in
baby
Wants no
more
Any
reason
Not
married
%
of
respondents

Theoretical grouping
Agreement with legal abortion under specified
circumstances, 2000 U.S. General Social Survey
0
20
40
60
80
100
Mother's
health*
Pregnant
due to
rape*
Defect in
baby*
Wants no
more
kids
Any
reason
Not
married
%
of
respondents
Health reasons Social reasons

Combining theoretical & empirical criteria
Descending dollar value of expenditures for
necessities and non-necessities,
2002 U.S. Consumer Expenditure Survey
$-
$3,000
$6,000
$9,000
$12,000
$15,000
S
h
e
l
t
e
r
+
u
t
i
l
i
t
i
e
s
F
o
o
d
A
p
p
a
r
e
l
a
n
d
s
e
r
v
i
c
e
s
T
r
a
n
s
p
o
r
t
a
t
i
o
n
P
e
r
s
o
n
a
l
i
n
s
&
p
e
n
s
i
o
n
s
A
l
l
o
t
h
e
r
h
o
u
s
i
n
g
H
e
a
l
t
h
c
a
r
e
E
n
t
e
r
t
a
i
n
m
e
n
t
C
a
s
h
c
o
n
t
r
i
b
u
t
i
o
n
s
M
i
s
c
e
l
l
a
n
e
o
u
s
E
d
u
c
a
t
i
o
n
P
e
r
s
o
n
a
l
c
a
r
e
A
l
c
o
h
o
l
i
c
b
e
v
e
r
a
g
e
s
T
o
b
a
c
c
o
p
r
o
d
u
c
t
s
R
e
a
d
i
n
g
Necessities Non-necessities

Pattern with a third variable
Agreement with legal abortion, by gender of respondent and
circumstances of abortion, 2000 U.S. General Social Survey
Organized by topic of abortion question
0
20
40
60
80
100
Mother's
health*
Pregnant
due to
rape*
Defect in
baby*
Wants
no more
kids
Any
reason
Not
married
%
of
respondents
Men
Women
Health reasons Social reasons
* difference between men and women is statistically significant at p<.05

Identifying theoretical criteria
Consult the published literature on
your topic to learn about theoretical
criteria for organizing your variables.
In new research areas, empirical
sorting may yield clusters with similar
response patterns that can then be
explored for conceptual overlap.

For self-guided data lookup
Why is it important? When is it used?
Researchers look up data for own
research questions, then organize the
data using empirical or theoretical
criteria.
How to organize data for such tasks?
 Alphabetical order
 Order of items from data collection instrument
 Standard ordering used in periodic reports

Alphabetical order
Widely familiar principle, e.g., used in
Phone book
Daily stock market report
Learned at an early age
Facilitates self-guided lookup

Ordering for a public data source
Order of items on original data
collection instrument
Users can refer to codebook
Easy to find the variables they need
Ordering used in periodic reports
Standardized from year to year for a given
topic

Summary
There is no one principle for
organizing numeric data that fits all
possible tasks.
Determine your main objective
Hypothesis testing or pattern description
Data reporting for others’ use
Choose the organizing principle
accordingly.

Organizing data in tables and charts: Criteria

More Related Content

Similar to Organizing data in tables and charts: Criteria (20)

More from Richard Gamaliel Cortez (6)

Recently uploaded (20)

Organizing data in tables and charts: Criteria