Heavy tail modeling and teletraffic data

• 成果类型: Article
• 署名作者: Resnick, SI
• 署名单位: Cornell University
• 刊物名称: ANNALS OF STATISTICS
• ISSN/ISSBN: 0090-5364
• DOI: 10.1214/aos/1069362376
• 发表日期: 1997
• 页码: 1805-1849
• 关键词: extreme-value theory; infinite variance; Regular Variation; Moving averages; limit theory; AUTOREGRESSIVE PROCESSES; statistical-analysis; Self-similarity; hill estimator; dependent data

摘要

Huge data sets from the teletraffic industry exhibit many nonstandard characteristics such as heavy tails and long range dependence. Various estimation mer;hods for heavy tailed time series with positive innovations are reviewed. These include parameter estimation and model identification methods for autoregressions and moving averages. Parameter estimation methods include those of Yule-Walker and the linear programming estimators of Feigin and Resnick as well estimators for tail heaviness such as the Hill estimator and the qq-estimator. Examples are given using call holding data and interarrivals between packet transmissions on a computer network. The li:mit theory makes heavy use of point process techniques and random set theory.