From anecdote to average to awareness

[ajschumacher]

Anecdote, Average, and Awareness: Show the data

Anecdotes can be useful, but they are limited. Averages, intended as antidotes to anecdote, solve the wrong problem by erasing individuals. Both approaches encourage misunderstanding groups as archetypes. Groups are collections of individuals, and whenever possible they should be presented as such, using tools such as histograms.

Rather than reduce to averages, convey as much information as possible about available data.

When statistics are possible, provide as much information as possible on distributions, display of the full distribution is possible and may be better.

anecdote is that part-for-whole metaphor: synecdoche

Yunus worm's eye view

anecdote is always true per se

Naive realism (but doesn't seem perfectly aligned)

epistemology for anecdote is in a sense easier; you can talk to the one person, see a picture of them...

rare things particularly bad for anecdote:

"Though a factor of sixteen is hardly a small effect, lung cancer is itself scarce enough to confuse our intuitions. The world is full of patterns that are too subtle or too rare to detect by eyeballing them, and a pattern doesn't need to be very subtle or rare to be hard to spot without a statistical lens." (page 54, HtMtWAU)

Gould "median isn’t the message" https://journalofethics.ama-assn.org/article/median-isnt-message/2013-01

That article was/is quite popular; see, e.g., “The median isn't the message”: How to communicate the uncertainties of survival prognoses to cancer patients in a realistic and hopeful way.

The title of course is a reference to "The medium is the message"

---

from https://planspace.org/20210330-how_to_make_the_world_add_up_by_harford/

"[Florence Nightingale] corresponded with the great Belgian statistician Adolphe Quetelet. Quetelet was the person who popularised the idea of taking the 'average' or 'arithmetic mean' of a group, which was a revolutionary way to summarise complex data with a single number." (page 233)

Two paragraphs just taken from Wikipedia:

"His most influential book was Sur l'homme et le développement de ses facultés, ou Essai de physique sociale, published in 1835 (In English translation, it is titled Treatise on Man, but a literal translation would be "On Man and the Development of his Faculties, or Essays on Social Physics"). In it, he outlines the project of a social physics and describes his concept of the "average man" (l'homme moyen) who is characterized by the mean values of measured variables that follow a normal distribution. He collected data about many such variables."

"Adolphe Quetelet also had a significant influence on Florence Nightingale who shared with him a religious view of statistics which saw understanding statistics as revealing the work of God in addition to statistics being a force of good administration. Nightingale met Quetelet in person at the 1860 International Statistical Congress in London, and they corresponded for years afterwards."

So it seems from this that he was mostly popularizing quantitative methods in the social sciences. He had some idea of the "average man" as a kind of Platonic Ideal (see Gould), and (at least in the interpretation of some) that variation around the mean is "error"...

---

Displaying Uncertainty With Shading https://www.tandfonline.com/doi/abs/10.1198/000313008X370843

Visualizing and comparing distributions with half-disk density strips https://arxiv.org/abs/2006.16063

"In somewhat the same fashion those little figures [reporting variance] that are missing from what are called “Gessell’s norms” have produced pain in papas and mamas. Let a parent read, as many have done in such places as Sunday rotogravure sections, that “a child” learns to sit erect at the age of so many months and he thinks at once of his own child. Let his child fail to sit by the specified age and the parent must conclude that his offspring is “retarded” or “subnormal” or something equally invidious. Since half the children are bound to fail to sit by the time mentioned, a good many parents are made unhappy. Of course, speaking mathematically, this happiness is balanced by the joy of the other fifty per cent of parents in discovering that their children are “advanced.” But harm can come of the efforts of the unhappy parents to force their children to conform to the norms and thus be backward no longer." (pages 44-45, How to Lie with Statistics)

[ajschumacher]

epistemology for anecdote is in a sense easier; you can talk to the one person, see a picture of them...

[ajschumacher]

On displaying distributions:

Analyst Institute uses violin plots (Analyst Institute’s 2020 Meta-Analysis: Persuasion Findings, "Understanding Meta-Analysis Violin Plots") to display results as if they have a whole posterior distribution, which I'm not sure they do, but regardless it's kind of a nice idea.

"A stem-and-leaf plot (or simply stemplot), was invented by John Tukey (The idea behind the stemplot can be traced back to the work of Arthur Bowley in the early 1900s.) in his paper “Some Graphic and Semigraphic Displays” in 1972." (Stem-and-Leaf Plot)

40 years of boxplots (Hadley Wickham and Lisa Stryjewski)

on anecdotes and averages, maybe some connection to Archetypal psychology? maybe not quite... what's that idea of an "archetypal chair" etc., the idea that we think of things in terms of characteristic representations?

[ajschumacher]

"For the most part 'anecdotal evidence' is an oxymoron." (page 18, Didau, What if everything you knew about education was wrong?)

[ajschumacher]

as quoted by Thinking, Fast and Slow https://planspace.org/2011/12/17/selections-from-and-thoughts-on/

Nisbett and Borgida summarize the results in a memorable sentence:

Subjects' unwillingness to deduce the particular from the general was matched only by their willingness to infer the general from the particular.

This is a profoundly important conclusion. People who are taught surprising statistical facts about human behavior may be impressed to the point of telling their friends about what they have heard, but this does not mean that their understanding of the world has really changed. The test of learning psychology is whether your understanding of situations you encounter has changed, not whether you have learned a new fact. There is a deep gap between our thinking about statistics and our thinking about individual cases. Statistical results with a causal interpretation have a stronger effect on our thinking than noncausal information. But even compelling causal statistics will not change long-held beliefs or beliefs rooted in personal experience. On the other hand, surprising individual cases have a powerful impact and are a more effective tool for teaching psychology because the incongruity must be resolved and embedded in a causal story. That is why this book contains questions that are addressed personally to the reader. You are more likely to learn something by finding surprises in your own behavior than be hearing surprising facts about people in general.

[ajschumacher]

In "Bernoulli's Fallacy":

"His [Quetelet's] goal, perhaps antagonized by the Baron de Keverberg's skepticism, was to investigate analytically all the ways people were the same or different and to create a theory of social physics, a set of laws governing society that could be an equivalent of Kepler's laws of planetary motion and other immutable principles of the hard sciences." (page 113)

This reminds me of psychohistory.

"He [Quetelet] would later be harshly ridiculed for his love of the normal distribution by statisticians like Francis Edgeworth, who wrote in 1922: “The theory [of errors] is to be distinguished from the doctrine, the false doctrine, that generally, wherever there is a curve with a single apex representing a group of statistics ... that the curve must be of the ‘normal’ species. The doctrine has been nick-named ‘Quetelismus,’ on the ground that Quetelet exaggerated the prevalence of the normal law.”" (page 122)

[ajschumacher]

"As Fisher wrote in Statistical Methods for Research Workers, “No human mind is capable of grasping in its entirety the meaning of any considerable quantity of numerical data. We want to be able to express all the relevant information contained in the mass by means of comparatively few numerical values. This is a purely practical need which the science of statistics is able to some extent to meet." (page 233, Bernoulli's Fallacy)

[ajschumacher]

https://en.wikipedia.org/wiki/Ecological_fallacy

[ajschumacher]

data visualization as the (an) answer...