“ Power corrupts.
PowerPoint corrupts absolutely.”
  — Edward R. Tufte

With the greatest respect to Professor Tufte, whom I consider my teacher,
I propose the design below as an improvement on the design
from his monograph, The Cognitive Style of PowerPoint,
summarized in Wired September 2003, pp 118-119.

Estimated survival rates by cancer site

% survival / standard error
5 year 10 year 15 year 20 year
Prostate
98.8
   

0.4
95.2
   

0.9
87.1
   

1.7
81.3
   

3.0
Thyroid
96.0
   

0.8
95.8
   

1.2
94.0
   

1.6
95.4
   

2.1
Testis
94.7
   

1.1
94.0
   

1.3
91.1
   

1.8
88.2
   

2.3
Melanomas
89.0
   

0.8
86.7
   

1.1
83.5
   

1.5
82.8
   

1.9
Breast
86.4
   

0.4
78.3
   

0.6
71.3
   

0.7
65.0
   

0.7
Hodgkin’s Disease
85.1
   

1.7
79.8
   

2.0
73.8
   

2.4
67.1
   

2.8
Corpus uteri, uterus
84.3
   

1.0
83.2
   

1.3
80.8
   

1.7
79.2
   

2.0
Urinary, bladder
82.1
   

1.0
76.2
   

1.4
70.3
   

1.9
67.9
   

2.4
Cervis, uteri
70.5
   

1.6
64.1
   

1.8
62.8
   

2.1
60.0
   

2.4
Larynx
68.8
   

2.1
56.7
   

2.5
45.8
   

2.8
37.8
   

3.1
Rectum
62.6
   

1.2
55.2
   

1.4
51.8
   

1.8
49.2
   

2.3
Kidney, renal pelvis
61.8
   

1.3
54.4
   

1.6
49.8
   

2.0
47.3
   

2.6
Colon
61.7
   

0.8
55.4
   

1.0
53.9
   

1.2
52.3
   

1.6
Non-Hodgkin’s
57.8
   

1.0
46.3
   

1.2
38.3
   

1.4
34.3
   

1.7
Oral cavity, pharynx
56.7
   

1.3
44.2
   

1.4
37.5
   

1.6
33.0
   

1.8
Ovary
55.0
   

1.3
49.3
   

1.6
49.9
   

1.9
49.6
   

2.4
Leukemia
42.5
   

1.2
32.4
   

1.3
29.7
   

1.5
26.2
   

1.7
Brain, nervous system
32.0
   

1.4
29.2
   

1.5
27.6
   

1.6
26.1
   

1.9
Multiple myeloma
29.5
   

1.6
12.7
   

1.5
7.0
   

1.3
4.8
   

1.5
Stomach
23.8
   

1.3
19.4
   

1.4
19.0
   

1.7
14.9
   

1.9
Lung and bronchus
15.0
   

0.4
10.6
   

0.4
8.1
   

0.4
6.5
   

0.4
Esophagus
14.2
   

1.4
7.9
   

1.3
7.7
   

1.6
5.4
   

2.0
Liver, bile duct
7.5
   

1.1
5.8
   

1.2
6.3
   

1.5
7.6
   

2.0
Pancreas
4.0
   

0.5
3.0
   

1.5
2.7
   

0.6
2.7
   

0.8
A table of bar graphs (small multiples): rich, informative, visually comparative.
A further improvement would depict the standard error as a dimmed zone between the two percentage bars, perhaps something like this:
       
Or perhaps the border between the two colors could have a slant, the more slant, the more standard error. But first I need a function that takes percent and standard error as input and returns the appropriate 4 percentages to display...

Discuss this on Edward Tufte’s web site.

(If the small type looks bad on your computer, try a Mac!)

http://Yost.com/information-design/powerpoint-corrupts/ - this page
2003-08-20 Created
Part of Dave Yost's web site - Please if you link to or cite this page