>The phrase is actually “The plural of anecdote is not evidence”.

I always thought the phrase was "The plural of anecdote is not data" but it looks like that is a misquote:

Nelson W. Polsby PS, Vol. 17, No. 4. (Autumn, 1984), pp. 778-781. Pg. 779: Raymond Wolfinger’s brilliant aphorism “the plural of anecdote is data” never inspired a better or more skilled researcher.

I e-mailed Wolfinger last year and got the following response from him:

“I said ‘The plural of anecdote is data’ some time in the 1969-70 academic year while teaching a graduate seminar at Stanford. The occasion was a student’s dismissal of a simple factual statement–by another student or me–as a mere anecdote. The quotation was my rejoinder. Since then I have missed few opportunities to quote myself. The only appearance in print that I can remember is Nelson Polsby’s accurate quotation and attribution in an article in PS: Political Science and Politics in 1993; I believe it was in the first issue of the year.”

So it looks like munificent is right and everyone that has downvoted should upvote and think better next time.

To add another link to the one Bumby has http://blog.danwin.com/don-t-forget-the-plural-of-anecdote-i...

which actually it makes a lot more sense to me this quote than the misquote because >You can’t collect a couple of anecdote and pretend it’s data.

sure but you can collect 10000 anecdotes, put them in a spreadsheet with some information about the people who said it, and suddenly you got data.

I mean that is basically what I thought to myself every time somebody said the plural of anecdote is not data but bit my tongue because not wanting to get into a war over it, and now I find out the original was actually exactly what I thought it should be.

Thanks munificent! Your name certainly applies for me.

Then allow me to coin an entirely new and original aphorism, let's call it Kibwen's Law:

"The plural of anecdote is not data."

The methodology of collecting anecdotes matters immensely. Merely collecting anecdotes based on whoever manages to comment in a random thread opens your collection process up to massive selection bias. In fact we even have a name for this process: a filter bubble. Every filter bubble in existence is the result of people assuming that not only is the population of their bubble representative of the average person (it's not), but also that people on either side of an issue will be equally likely to offer their anecdote (they're not).

Without rigorous collection methodology, anecdotes do not sum to data.

(Note that this comment says nothing about the broader topic of omicron severity; I don't have data, listen to people who do.)

maybe it's just the anecdote you wish to share is unlikely to become part of a selection of data.

But that's not as pithy.

Pedantically, even an anecdote is data...of some sort.

> you can collect 10000 anecdotes, put them in a spreadsheet with some information about the people who said it, and suddenly you got data.

You can, but that's not a controlled study. The anecdotes can't be verified. So that data is not worth citing. I wish it were, which would make science a lot easier.

This depends on the context and the question. Some empiric observations are conclusive and more than enough, other not. Nice slogans fit great into simple problems but not so accurately into more complex ones. Science is more than just a bunch of math.