A technique for estimating the bias and standard deviation of an estimate.

Suppose we have a sample x = (x1, x2,...xn) and wish to estimate the bias and standard error of an estimator Θ. The jackknife focuses on the samples that leave out one observation at a time: the i-th jackknife sample consists of the data with the i-th observation removed.

Links to this page

© djmw, November 1, 2014