Another year, another group of Nobel Laureates: I’d like to take you on a brief tour of this famous data set from the basic to the absurd…
Firstly, with some plots of my own – I often get incredulous looks when people find out data analysis and visualisation is a hobby of mine! I’m a particular fan of Edward Tufte, whether you’re familiar with his work or not, I’d appreciate constructive criticism of my efforts. Latterly I’ll turn to the classic correlation ≠ causation, with Tyler Vigen’s website being worth a browse if you haven’t come across it before!
I’ve attempted to plot the basic characteristics of Nobel Laureates (birth, prizewinning year, death and gender) over time, though with so many data points a few aspects are particularly highlighted: the years in which there were no prizes awarded (particularly during the World Wars) and the increasing number of female Laureates (in red).
Other aspects partially noticeable in the plot above include the increasing number of shared prizes (more densely positioned lines) and the increasing age of recipients – both explored in the plot below.
While the average age started rapidly rising around 1960, the time between discovery and prize seems to have been increasing since the start (though less pronounced than for Physics):
Moving onto the tenuous: a “study” found that “the births of Medical Nobel Prize Winners are unevenly distributed among the (astrological) signs. This has produced significant correlations, that are arguably consistent with traditional characteristics of the traits of zodiacal signs.”
Intrigued, I decided to explore the, similarly arbitrary, birth months of Nobel prizewinners in Medicine or Physiology. I calculated the expected % through scaling the number of births per month in a certain country according to the proportion of prizewinners born in that country. Thus June is the most frequent birth month of Nobel Prizewinners (or Geminis if that floats your boat)!
Another exercise in correlation ≠ causation is the paper by Franz H. Messerli (2012) exploring the correlation between a country’s level of chocolate consumption and the number of Nobel Laureates per 10 million population – as a surrogate for cognitive function (!).
While the BBC and the Information is Beautiful Studio have calculated the most common characteristics of Nobel Laureates to create a “recipe for success”:
One can only hope that in the future the proportion of female Laureates will increase and “facial hair” will no longer be included, even in jest, as a predictor of being a Nobel Laureate!
However, perhaps just one example of a barrier to this is the tendency of elite male faculty, especially Nobel Prize Laureates in Medicine/Physiology and Chemistry, to employ fewer female postdocs and graduate students (Sheltzer and Smith, 2014) possibly due to conscious or unconscious bias or due to self-selection on the part of female scientists.
While that would be a slightly depressing point to end on, it is relevant to note that CRISPR/Cas9 has been tipped for Nobel Prize glory so perhaps come 2017 we may see Emmanuelle Charpentier, Jennifer Doudna and Feng Zhang announced as Nobel Laureates? By that point, it’ll be time for me to analyse the Nobel Prize data set once more – stay tuned!
Messerli, F. H. (2012) Chocolate Consumption, Cognitive Function, and Nobel Laureates. New England Journal of Medicine. 367 (16), 1562–1564.
Sheltzer, J. M. & Smith, J. C. (2014) Elite male faculty in the life sciences employ fewer women. Proceedings of the National Academy of Sciences. 111 (28), 10107–10112.