JSTOR is a not-for-profit service that helps scholars, researchers, and students discover, use, and build upon a wide range of content in a trusted digital archive. We use information technology and tools to increase productivity and facilitate new forms of scholarship. For more information about JSTOR, please contact support@jstor.org.. Biometrika Trust is collaborating with JSTOR to digitize, preserve and extend access to Biometrika.
SUMMARYThe jackknife is now well known as a widely applicable bias-reduction tool, with the added advantages of Tukey's variance estimator, and in certain applications, a gain in precision. In this paper a new family of jackknives is introduced, together with a variance estimator. The family includes the ordinary, first-order, and second-order jackknives as special cases and the variance estimator includes Tukey's as a special case. A sample-based decision rule for choosing a member of the family, intended to achieve a gain in precision over either order of jackknife, is given. The success of the rule is examined by simulation in estimation of the reciprocal of the parent mean and in ratio estimation.