Jackknife variance estimator for time series glms

Usage

lele.glm(glm.obj, times, lag)

Arguments

glm.obj Generalised linear model object
times vector of times at which response was observed
lag Correlation lag

Description

Estimates the covariance matrix for the generalised linear model using Lele's time series jackknife. This is strictly valid when the correlation is only non-zero for finitely many lags, but works provided the correlation is approximately zero beyond the specified lag.

Value

covariance matrix

Author(s)

Thomas Lumley

References

Lele (1991) "Jackknifing Linear Estimating Equations: Asymptotic Theory and Applications in Stochastic Processes" JRSSB 53:253𤫻

See Also

jack.glm,weave.trunc

Examples