A Note on Skewness in Regenerative Simulation
2011 (English)In: Communications in statistics. Simulation and computation, ISSN 0361-0918, E-ISSN 1532-4141, Vol. 40, no 1, 45-57 p.Article in journal (Refereed) Published
The purpose of this article is to show, empirically and theoretically, that performance evaluation by means of regenerative simulation often involves random variables with distributions that are heavy tailed and heavily skewed. This, in turn, leads to the variance of estimators being poorly estimated, and confidence intervals having actual coverage quite different from (typically lower than) the nominal one. We illustrate these general ideas by estimating the mean occupancy and tail probabilities in M/G/1 queues, comparing confidence intervals computed from batch means to various intervals computed from regenerative cycles. In addition, we provide theoretical results on skewness to support the empirical findings.
Place, publisher, year, edition, pages
2011. Vol. 40, no 1, 45-57 p.
ABC interval, Batch means, Busy cycle, Busy period, Coverage probability, Fieller test, Jackknife, M, G, 1 queue, Regenerative process, Regenerative simulation, Skewness
Probability Theory and Statistics
IdentifiersURN: urn:nbn:se:kth:diva-27381DOI: 10.1080/03610918.2010.526740ISI: 000284410600003ScopusID: 2-s2.0-78649522985OAI: oai:DiVA.org:kth-27381DiVA: diva2:376770
QC 201012132010-12-132010-12-132010-12-13Bibliographically approved