Consider the example of sample mean discussed below (14.1). Showed that, in this case, the right side of (14.8) is equal to s2/n, where s2 =

(n − 1)

−1



n i=1(Xi − ¯ X)2 is the sample variance. Therefore, we have E{:varJ( ˆ θ)} = var( ˆ θ); in other words, the jackknife variance estimator is unbiased.