An Unbalanced Jackknife
Miller, Rupert G.
Ann. Statist., Tome 2 (1974) no. 1, p. 880-891 / Harvested from Project Euclid
It is proved that the jackknife estimate $\tilde{\theta} = n\hat{\theta} - (n - 1)(\sum \hat{\theta}_{-i}/n)$ of a function $\theta = f(\beta)$ of the regression parameters in a general linear model $\mathbf{Y} = \mathbf{X\beta} + \mathbf{e}$ is asymptotically normally distributed under conditions that do not require $\mathbf{e}$ to be normally distributed. The jackknife is applied by deleting in succession each row of the $\mathbf{X}$ matrix and $\mathbf{Y}$ vector in order to compute $\hat{\mathbf{\beta}}_{-i}$, which is the least squares estimate with the $i$th row deleted, and $\hat{\theta}_{-i} = f(\hat\mathbf{\beta}_{-i})$. The standard error of the pseudo-values $\tilde{\theta}_i = n\hat{\theta} - (n - 1)\hat{\theta}_{-i}$ is a consistent estimate of the asymptotic standard deviation of $\tilde{\theta}$ under similar conditions. Generalizations and applications are discussed.
Publié le : 1974-09-14
Classification:  15,  35,  Jackknife,  pseudo-value,  general linear model,  multiple regression,  asymptotic normality,  62G05,  62E20
@article{1176342811,
     author = {Miller, Rupert G.},
     title = {An Unbalanced Jackknife},
     journal = {Ann. Statist.},
     volume = {2},
     number = {1},
     year = {1974},
     pages = { 880-891},
     language = {en},
     url = {http://dml.mathdoc.fr/item/1176342811}
}
Miller, Rupert G. An Unbalanced Jackknife. Ann. Statist., Tome 2 (1974) no. 1, pp.  880-891. http://gdmltest.u-ga.fr/item/1176342811/