# Clustering and hitting times of threshold exceedances and applications

@article{Markovich2017ClusteringAH, title={Clustering and hitting times of threshold exceedances and applications}, author={Natalia M. Markovich}, journal={Int. J. Data Anal. Tech. Strateg.}, year={2017}, volume={9}, pages={331-347} }

We investigate exceedances of the process over a sufficiently high threshold. The exceedances determine the risk of hazardous events like climate catastrophes, huge insurance claims, the loss and delay in telecommunication networks.
Due to dependence such exceedances tend to occur in clusters. The cluster structure of social networks is caused by dependence (social relationships and interests) between nodes and possibly heavy-tailed distributions of the node degrees. A minimal time to reach a… Expand

#### 3 Citations

Nonparametric Analysis of Extremes on Web Graphs: PageRank Versus Max-Linear Model

- Computer Science
- 2017

The cluster structure in large networks by means of clusters of exceedances regarding the influence characteristics of nodes is analyzed, using PageRank and the Max-Linear model and comparing their distributions and dependence structure. Expand

A Caching policy driven by clusters of high popularity

- Computer Science
- 2016 International Wireless Communications and Mobile Computing Conference (IWCMC)
- 2016

A mixture of m-dependent Markov and Poisson renewal processes is proposed as example of an inter-request time model and the hit/miss probabilities of such caching policy are presented and cache size estimation is considered. Expand

Distributed Computer and Communication Networks

- Communications in Computer and Information Science
- 2017

The Internet of Things (IoT) undergoes fundamental changes, expanding its infrastructure with more advanced and mobile devices. As the IoT develops, the existing cellular communication technologies… Expand

#### References

SHOWING 1-10 OF 34 REFERENCES

Modeling clusters of extreme values

- Mathematics
- 2014

In practice it is important to evaluate the impact of clusters of extreme observations caused by the dependence in time series. The clusters contain consecutive exceedances of time series over a… Expand

Extremes Control of Complex Systems With Applications to Social Network

- Computer Science, Mathematics
- 2015

The paper contributes to the comparison of sampling techniques in complex networks by means of the first hitting time, that is the minimal time required to reach a large node, and the mean and the distribution of thefirst hitting time is shown to be determined by the so called extremal index. Expand

Distribution and Dependence of Extremes in Network Sampling Processes

- Mathematics, Computer Science
- 2014 Tenth International Conference on Signal-Image Technology and Internet-Based Systems
- 2014

This work abstracts the dependence and the statistics of extremes into a single parameter that appears in Extreme Value Theory, called external index (EI), and proposes the use of EI as a parameter to compare different sampling procedures. Expand

Inference for the limiting cluster size distribution of extreme values

- Mathematics
- 2009

Any limiting point process for the time normalized exceedances of high levels by a stationary sequence is necessarily compound Poisson under appropriate long range dependence conditions. Typically… Expand

Subexponential asymptotics for stochastic processes : extremal behavior, stationary distributions and first passage probabilities

- Mathematics
- 1998

Consider a reflected random walk Wn+1 = (W-n +X-n)(+), where X-o, X-1,... are i.i.d. with negative mean and subexponential with common distribution F. It is shown that the probability that the… Expand

Beyond random walk and metropolis-hastings samplers: why you should not backtrack for unbiased graph sampling

- Mathematics, Computer Science
- SIGMETRICS '12
- 2012

This paper proposes non-backtracking random walk with re-weighting (NBRW-rw) and MH algorithm with delayed acceptance (MHDA) which are theoretically guaranteed to achieve, at almost no additional cost, not only unbiased graph sampling but also higher efficiency (smaller asymptotic variance of the resulting unbiased estimators) than the SRw-rw and the MH algorithm, respectively. Expand

A Comparison of Methods for Estimating the Extremal Index

- Mathematics
- 2000

The extremal index, θ (0≤θ≤1), is the key parameter when extending discussions of the limiting behavior of the extreme values from independent and identically distributed sequences to stationary… Expand

Algorithms and Models for the Web-Graph

- Computer Science
- Lecture Notes in Computer Science
- 2004

This paper considers several families of random graphs that grow in time by the addition of vertices and edges in some ‘uniform’ manner and investigates the connection between the existence of a giant component and the connectedness of the final infinite graph. Expand

A simple analysis of customer impatience in multi-server queues

- Computer Science
- 2011

This paper is an attempt to model such a reneging phenomenon along with balking in a multi-server queuing scenario and closed form expressions of a number of performance measures are presented. Expand

Estimating the Extremal Index

- Mathematics
- 1994

SUMMARY The extremal index is an important parameter measuring the degree of clustering of process. The extremal index, a parameter in the interval [0, 1], is the reciprocal of the mean cluster size.… Expand