I used to know this 25-cent word, and I have forgotten it. It describes a phenomenon where common descriptive statistics like mean and variance misrepresent the individuals or maybe the phenomenon itself. (I don't know because I can't look it up!) I believe it begins with an e, probably an en- or eu-. Does it sound familiar to anyone?

"Children's classroom learning should not be reduced to test scores, because learning is -------- "

  • Requests for a single word are best accompanied by a sample sentence in which the desired word might appear as a blank.
    – WS2
    Commented Jul 3, 2018 at 15:31
  • Enthetic, eustatic, endocastic, something like that. Not ecological, not epistemic, not endogenous.
    – J Kelly
    Commented Jul 3, 2018 at 15:57
  • Enigmatic might just work here, but it's a stretch.
    – Phil Sweet
    Commented Jul 4, 2018 at 0:45

4 Answers 4


Are you talking about outliers, or potentially the results of any dataset with outliers?

If you have a set of restaurant ratings:

1, 4.5,4.5,5

The mean is skewed significantly by the outlier of 1 (mean =3.75) and a mean of 3.75 also does not represent the outlier, 1, well.

  • Not exactly. Conceptually similar but more descriptive of the whole collection or phenomenon. Income is ________ because of the skewing at both the low and high ends of the range.
    – J Kelly
    Commented Jul 3, 2018 at 15:41
  • Variant? As in talking about how large the spread of data is?
    – jmrpink
    Commented Jul 3, 2018 at 15:48
  • My example here turned out to be inapt.
    – J Kelly
    Commented Jul 4, 2018 at 16:33

Phenomena that can't be well described by statistics are generally referred to as being statistically "intractable" meaning you can't get a handle on them that way.

  • Ok, that is roughly the meaning I want. Now can you think of the technical term, possibly from social science, that begins with an "e"?
    – J Kelly
    Commented Jul 3, 2018 at 15:46
  • @JKelly Sorry not off the top of my head no. I'll keep thinking and get back to you.
    – Ash
    Commented Jul 3, 2018 at 15:48
  • I am only being picky because I want to chase down related materials with google. Thanks!
    – J Kelly
    Commented Jul 3, 2018 at 15:49
  • @JKelly You can have a data set that yields "enigmatic results", results that don't convey what you expect given the general shape of the raw data field.
    – Ash
    Commented Jul 3, 2018 at 15:52


From Wiktionary:

Of, pertaining to, or as a consequence of entropy.

Entropy from Wiktionary:

(statistics, information theory, countable) A measure of the amount of information and noise present in a signal.

The tendency of a system that is left to itself to descend into chaos.

You might also want to read the related Q&A on stats.stackexchange.

  • Thanks, you sent me looking down the right (physics) path!
    – J Kelly
    Commented Jul 4, 2018 at 16:27

The word was "ergodic" -- "the ensemble average equals the time average" -- and the concept I was trying to research was "nonergodic." The meaning is a little different than I'd recalled. It's more like a phenomenon that's reliant on its history, but I couldn't discover that without the actual term. Thanks to all!

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge you have read our privacy policy.

Not the answer you're looking for? Browse other questions tagged or ask your own question.