Biology, images, analysis, design...
Use/Abuse Principles How To Related
"It has long been an axiom of mine that the little things are infinitely the most important" (Sherlock Holmes)

Search this site



Just a note

Although the Swiss Army knife is immensely popular, has spawned many imitations, and is standard issue in virtually every army on Earth - by some strange quirk of fate, it is not used by the Swiss army.

Historically, the idea of jackknife statistics originated with the idea of (randomly) dividing a sample into two (equal) parts, calculating two estimates, and comparing their mean with the original estimate - or estimating the variance of the original estimate from their variance.

So although -j (or (-j)) usually denotes an estimate where just one observation (the jth) is missed out, (-1) (or -1), indicates the estimate is based upon n - 1 observations. From which it follows that, (-m) is sometimes used to denote an estimate based upon n - m observations. Nowadays this convention is seldom used because, in general, just omitting one observation produces more reliable results - however, you may encounter this notation in 'higher order' jackknife estimators.