Going back to the post 8 Ways You Can Visualise Proportions,  I provided a WAY 8 using the Nightingale rose graph – or the polar area diagram to visualise proportions, and this is a follow-up on WAY 8 from that post.

The Nightingale rose graph was a diagram by Florence Nightingale (1820 – 1910). Nightingale, an Anglican English nurse became famous for tending to the wounded soldiers during the Crimean War, she loved doing night rounds and was dubbed “The Lady with the Lamp”, she laid the foundation of professional nursing and established her nursing school at St Thomas’ Hospital, London in 1860, new nurses take the Nightingale Pledge, and nurses celebrate the annual International Nurses Day on her birthday. Florence Nightingale was also a writer and an accomplished statistician  who in 1858, became the first female fellow of the Statistical Society of London (now Royal Statistical Society).

Florence Nightingale met William Farr, the Compiler of Abstracts in the General Registry Office and an innovative statistician at a dinner party in 1856. Both cared deeply about improving the world through sanitation; both understood the importance of meticulous records in providing the evidence needed to bring about change.

Now let’s move on and look at the original diagram drawn by Nightingale as below, “Diagram of the causes of mortality in the army in the East”  dated 1858 was published in Notes on Matters Affecting the Health, Efficiency, and Hospital Administration of the British Army and sent to Queen Victoria in 1858.

You can view a 1280p X 804p of this graphic from the post 8 Ways You Can Visualise Proportions

The legend of this graphic above displays the causes of the deaths of soldiers during the Crimean war. The legend explains that each wedge is divided into three categories.:

• “Preventible or Mitigable Zymotic Diseases” (infectious diseases, including cholera and dysenter), in blue
• those that were the results of wounds, in red
• those due to all other causes, in black.

The legend also explains that:

• the black line across the red triangle in Nov. 1854 marks the boundary of the deaths from all other causes during the month.
• in October 1854, & April 1855, the black area coincides with the red,
• in January & February 1856, the blue coincides with the black.

Note that the graphic on the right starts from April 1854 and ends March 1855, while the the graphic on the left April 1855 starts from April 1855 and ends March 1856.

In November 1854, the number if wounds was very high as compared to other months, so it must be a period of heavy fighting, as far more soldiers died from infection than from wounds.

Now, I like to compare Nightingale’s diagram as compared to pie charts we draw today.

As a simple example, here is a frequency distribution table showing the distribution of “marital status” from a counseling center survey.

To construct a pie chart,  the percentage of all cases that fall into each category(single, married, divorced) of the variable(marital status) is computed. A circle (the pie) is divided into segments (slices) proportional to the percentage distribution. Since a circle’s circumference is 360°, 180° (or 50%) is apportioned for the first category, 126° (35%) for the second, and 54° (15%) for the last category.

The pie chart displays like this:

From the graphic of Nightingale’s diagram which resembles a pie chart, it can be seen that each wedge is drawn from the common centre. As I have described above, in pie charts, we draw the area of each wedge proportional to the figure it stands for.

Thus her diagram is different from the common pie chart we know as follows:

• the data is plotted by month in 30-degree wedges. In each month, red represents deaths by injury, blue death by disease, and black death by other causes
• the radius of each slice (the distance from the common centre to the outer edge) is altered to achieve the area for each category; she measured each proportion along the linear radius distance
• the red, black and blue wedges are all measured from the centre, so some areas mask parts of others unlike the wedges which appear distinct and separate like in the pie chart above
• the areas of the wedges are not proportional; I tend to agree with Henry Woodbury that Nightingale used the word area in the generic sense of section or range as she made in her annotation, but the data actually maps to the radius of each wedge
• the numbers of deaths from the various causes are not stated but shows their relative size

Nightingale’s diagram, often referred to as Nightingale’s Rose or Nightingale’s Coxcomb –  although she did not refer to them as such, is so visually interesting and so iconic (a rose, a coxcomb) like when I first saw her diagram in Randy Krum’s blog , I tend to agree to Henry, so beware the inherent risks in visual explanation, as more often that not we assume its conclusions without examining its data(Henry, W. 2008)..

I think too that it better sense using a stacked bar chart that introduces a scale, more readable labels, and a single chart for the entire 1854-1856 period. These changes provide context and continuity, and make clear the two campaigns of the war as can be viewed below:

Source : dd.dynamicdiagrams.com

or like this:

Source : dd.dynamicdiagrams.com

Lesson learned:

Because of her novel methods of communicating data by creating graphs as we have seen above to highlight the death toll from diseases above the death toll from wounds in the Crimean War, Nightingale returned to Great Britain and continued to fight for better conditions in hospitals, and this made her a pioneer in establishing the importance of sanitation in hospitals.

Abridged, and adapted from the following sources:

1. Coolinfographics, Randy Krum’s blog
2. Charts, Worth a thousand words, Dec 19, 2007, The Economist
3. Nightingale’s Rose, By Henry Woodbury, Jan 9, 2008, dd.dynamicdiagrams.com
4. Nightingale’s ‘Coxcombs’, May 11, 2008, understandinguncertainty.org
5. Statistics: A Tool for Social Research, Eighth Edition Joseph F. Healey, 2009, Wadsworth Cengage Learning, Belmont, CA, USA
6. Wikipedia