Skip to Main Content
Statistical Computing in Nuclear Imaging
book

Statistical Computing in Nuclear Imaging

by Arkadiusz Sitek
December 2014
Intermediate to advanced content levelIntermediate to advanced
275 pages
9h 12m
English
CRC Press
Content preview from Statistical Computing in Nuclear Imaging
124 Statistical Computing in Nuclear Imaging
One approach that should always be used for testing for the conver
gence
to the equilibrium is to lo ok at the Markov trace which is a plot of some QoI
vs. the number of Markov step as illustrated in Figure 4.10. The trace shows
the evidence of poor mixing and can also provide an estimate of the burn-in
period. It must be cautioned however that the actual burn-in time c an be
much longer than sugg ested by the trace, but it is often obvious based o n the
trace that the burn-in is incomplete.
A more formal test for re aching the equilibrium is also available. For ex-
ample, suppose we determined the po int
Become an O’Reilly member and get unlimited access to this title plus top books and audiobooks from O’Reilly and nearly 200 top publishers, thousands of courses curated by job role, 150+ live events each month,
and much more.
Start your free trial

You might also like

Industrial Statistics with Minitab

Industrial Statistics with Minitab

Pere Grima Cintas, Lluis Marco Almagro, Xavier Tort-Martorell Llabres
Learning Bayesian Models with R

Learning Bayesian Models with R

Hari Manassery Koduvely

Publisher Resources

ISBN: 9781439849347