Skip to main content
Author: N.G. Shephard
4 results found.
Return to Latest Publications
Andrew C Harvey and N.G. Shephard
A stochastic variance model may be estimated by quasi-maximum likelihood procedure by transforming to a linear state space form. The properties of observations corrected for heteroscedasticity can be derived. A model wit...Read more...
Siem Jan Koopman and N.G. Shephard
The score vector for a time series model which fits into the Gaussian state space form can be approximated by numerically differentiating the log-likelihood. If the parameter vector is of length p, this involves the runn...Read more...
A.C. Atkinson and N.G. Shephard
Deletion diagnostics are developed for structural time series models. These show the effect of the deletion of individual observations on residuals and on the estimates of regression parameters. The methods are extended ...Read more...