I've seen a number of references to a "solve-the-equation" approach (or method, etc) to choose a kernel density estimation (KDE) bandwidth, but different papers use different citations, and none of them seem to give a pedagogical explanation for this, or the origin of the term.

For example one paper refers to Sheather & Jones 1991 but that paper doesn't use this phrase at all. Similarly for the references in the Wikipedia KDE page which also uses the term.

  • $\begingroup$ Simon Sheather and Chris Jones use the term "plug in" -- is that what you mean by "solve-the-equation"? (e.g. see top of page 685 of your ref) which term they appear to attribute to Park and Marron (1990) but list a history of papers developing the ideas leading up to that. $\endgroup$ – Glen_b Mar 3 '17 at 4:06
  • $\begingroup$ Hi @Glen_b, I'm not sure --- I don't know what this term is supposed to mean, so I can't really compare it to "plug in"... unfortunately. $\endgroup$ – DilithiumMatrix Mar 3 '17 at 15:52

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.