Abstract. Huge data sets from the teletraffic industry exhibit many non-standard characteristics such as heavy tails and long range dependence. Various estimation methods 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 inter-arrivals between packet transmissions on a computer network. The limit theory makes heavy use of point process techniques and random set theory. 1.
|
449
|
Analysis, Modeling and Generation of Self-Similar VBR Video Traffic
– Garrett, Willinger
- 1994
|
|
101
|
Statistics of Extremes
– Gumbel
- 1988
|
|
100
|
Stable Non-Gaussian Random Processes
– Samorodnitsky, Taqqu
- 1994
|
|
90
|
Self-Similarity in High-Speed Packet Traffic: Analysis and Modeling of Ethernet Traffic Measurements
– Willinger, Taqqu, et al.
- 1995
|
|
71
|
Statistical analysis of CCSN/SS7 traffic data from working subnetworks
– Duffy, McIntosh, et al.
- 1994
|
|
67
|
Heavy tails and long range dependence in on/off processes and associated fluid models
– Heath, Resnick, et al.
- 1998
|
|
49
|
Extreme Value Theory in Engineering
– Castillo
|
|
39
|
Extreme Values, Regular Variation and
– Resnick
- 1987
|
|
37
|
Traffic models for ISDN data users: Office Automatiion application
– Meier-Hellstern, Wirth, et al.
- 1991
|
|
34
|
Time Series: Theory and Methods. 2nd edition
– Brockwell, Davis
- 1991
|
|
33
|
On some simple estimates of an exponent of regular variation
– Hall
- 1982
|
|
30
|
On Regular Variation and its Application to the Weak Convergence of the Sample Extremes
– Haan
- 1970
|
|
28
|
Point processes, regular variation, and weak convergence
– Resnick
- 1986
|
|
27
|
Limit theory for moving averages of random variables with regularly varying tail probabilities
– Davis, Resnick
- 1985
|
|
26
|
Tsiolis. The impact of autocorrelation on queueing systems
– Livny, Melamed, et al.
- 1993
|
|
25
|
Limit theory for the sample covariance and correlation functions of moving averages
– Davis, Resnick
- 1986
|
|
25
|
Regular Variation, Extensions and Tauberian Theorems
– Geluk, Haan
- 1987
|
|
22
|
Long-range dependence in Variable-bit rate video traffic
– Beran, Sherman, et al.
- 1995
|
|
20
|
Consistency of Hill's estimator for dependent data
– Resnick, Starica
- 1995
|
|
19
|
A simple approach to inference about the tail of a distribution
– Hill
- 1975
|
|
18
|
Limit theory for bilinear processes with heavy tailed noise
– Davis, Resnick
- 1996
|
|
16
|
On the structure of stationary stable processes
– Rosiński
- 1995
|
|
14
|
Statistics for Long-Memory
– Beran
- 1994
|
|
14
|
On the frequency of Large Stock Returns: Putting Booms and Busts into Perspectives
– Jansen, Vries
- 1991
|
|
13
|
Parameter estimation for ARMA models with infinite variance innovations
– Mikosch, Gadrich, et al.
- 1995
|
|
12
|
Regular Variation, Encyclopedia of Mathematics and its Applications
– Bingham, Goldie, et al.
- 1987
|
|
12
|
Why non-linearities can ruin the heavy tailed modeler's day
– Resnick
- 1997
|
|
11
|
More limit theory for the sample correlation function of moving averages
– Davis, Resnick
- 1985
|
|
11
|
Performance decay in a single server exponential queueing model with long range dependence
– Resnick, Samorodnitsky
- 1997
|
|
10
|
A Moment Estimator for the Index of an Extreme Value Distribution
– Dekkers, Einmahl, et al.
- 1989
|
|
9
|
Tail and quantile estimation for strongly mixing stationary sequences
– Rootzen, Leadbetter, et al.
- 1990
|
|
8
|
Tail estimates motivated by extreme value theory
– Davis, Resnick
- 1984
|
|
8
|
On tail estimation using dependent data
– Hsing
- 1991
|
|
7
|
Analyzing Telecommunications Traffic Data from Working Common Channel Signaling Subnetworks
– Duffy, McIntosh, et al.
- 1993
|
|
7
|
Estimation for autoregressive processes with positive innovations, Stochastic Models 8
– Feigin, Resnick
- 1992
|
|
7
|
Pitfalls of fitting autoregressive models for heavy-tailed time series
– Feigin, Resnick
- 1996
|
|
7
|
Random Measures, Third edition
– Kallenberg
- 1983
|
|
7
|
A strong invariance theorem for the tail empirical process
– Mason
- 1988
|
|
6
|
On the estimation of the extreme value index and large quantile estimation
– Dekkers, Haan
- 1989
|
|
6
|
Limit distributions for linear programming time series estimators
– Feigin, Resnick
- 1994
|
|
6
|
Testing for independence in heavy tailed and positive innovation time series, Stochastic Models 11
– Feigin, S, et al.
- 1995
|
|
6
|
Applied non-Gaussian processes
– Grigoriu
- 1995
|
|
6
|
of large numbers for sums of extreme values, Ann. Probability 10
– Mason, Laws
- 1982
|
|
6
|
Smoothing the Hill estimator, To appear
– Resnick, Starica
- 1996
|
|
4
|
Central limit theorems for sums of extreme values
– Csorgo, Mason
- 1985
|
|
4
|
Some results on the influence of extremes on the bootstrap, Ann. Inst. Henri Poincare 29
– Deheuvels, Mason, et al.
- 1993
|
|
4
|
Optimal choice of sample fraction in extreme value estimation
– Dekkers, Haan
- 1993
|
|
4
|
Second order regular variation, convolution and the central limit theorem. Preprint. Available as TR1133 at http://www.orie.cornell.edu/trlist/trlist.html
– Geluk, Haan, et al.
- 1995
|
|
4
|
Necessary conditions for the bootstrap of the mean
– Gine, Zinn
- 1989
|
|
4
|
Processus Ponctuels, Ecole d'Et'e de Probabilit'es de Saint-Flour VI
– Neveu
- 1977
|
