Practical considerations of the jackknife estimator of variance for generalized estimating equations

Lipsitz, Dear and Zhao (1994) proposed a "one-step" Jackknife estimator of the variance based on Wu's (1986) jackknife and showed its asymptotic equivalence to the robust variance estimator of White (1982) and Liang and Zeger (1986). In this paper an asymptotically equivalent estimator is proposed which avoids the Newton-Raphson or Fisher scoring step of the estimator proposed by Lipsitz, Dear and Zhao. Hence, summation in univariate models can be avoided.