For some regressions we find it useful to focus on extreme values, and so we discard middling dependent values (which we might call "noise") from data in order to find relationships that hold at data extrema.

Does this step of discarding middling data values have a name? (It seems like the "opposite" of Winsorizing, and I have seen it in varied applications, but never given a name.)


Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Browse other questions tagged or ask your own question.