On Modeling Change Points in Non-Homogeneous Poisson Processes

Ruggeri, Fabrizio; Sivaganesan, Siva

doi:10.1007/s11203-005-6100-y

Cited by 31 publications

(14 citation statements)

References 14 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This assumption means in our setting that requests are independent of the Web service reputation, which changes with time. To better model the dynamics of requests that depend on reputation, we use the non-homogeneous Poisson process [12], which is a Poisson process with dynamic rate λ i (x) denoting the mean number of requests received by Web service i at time moment x, where x belongs to the time unit t. Here we should distinguish between the time unit t (i.e. the interval [1, t]) and time moment x in the sense that the moment is inside the time unit.…”

Section: A Service Requestmentioning

confidence: 99%

“…For simplicity reasons and to achieve a high focus, we restrict the reputation model to two crucial parameters: satisfaction and popularity and analyze the impacts that these parameters have on one another in continuous service selection processes (considering other parameters is our plan for future work). In this mechanism, we use the non-homogenous Poisson [12] as the probability distribution that models the arrival of requests for a typical Web service (the motivations and reasons behind using this distribution will be discussed in Section III). We aim to theoretically analyze the impacts that parameters have on one another and deduce cases where the Web service has a clear incentive to change its acting strategy.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Analyzing the Relationships between some Parameters of Web Services Reputation

Khosravifar

Moazin

2010

2010 IEEE International Conference on Web Services

View full text Add to dashboard Cite

Abstract-In this paper, we provide an analysis of the impacts of some reputation parameters that an agent-based Web service holds while being active in the environment. To this end, we deploy a reputation model that ranks the Web services with respect to their popularity in the network of users. We model and analyze the arrival of requests and study their impacts on the overall reputation. The Web services may be encouraged to handle the peak loads by gathering to a group. Besides theoretical discussions, we also provide significant results, which elaborate more on the details of the system parameters. We extend the details of these results to empirical results and link the observations of the implemented environment to the results that we theoretically obtain.

show abstract

Section: A Service Requestmentioning

confidence: 99%

Section: Introductionmentioning

confidence: 99%

Analyzing the Relationships between some Parameters of Web Services Reputation

Khosravifar

Moazin

2010

2010 IEEE International Conference on Web Services

View full text Add to dashboard Cite

show abstract

“…Raftery and Akman (1986) consider a Bayesian analysis for homogeneous Poisson processes (HPP) in the presence of a change-point. Ruggeri and Sivaganesan (2005) introduce a Bayesian analysis for change-points in non-homogeneous Poisson processes considering PLP and dealing with a random number of change-points.…”

Section: A Bayesian Estimation Of the Parametersmentioning

confidence: 99%

Non-homogeneous Poisson models with a change-point: an application to ozone peaks in Mexico city

Achcar¹,

Rodrigues²,

Paulino

et al. 2009

Environ Ecol Stat

View full text Add to dashboard Cite

In this paper, we use some non-homogeneous Poisson models in order to study the behavior of ozone measurements in Mexico City. We assume that the number of ozone peaks follows a non-homogeneous Poisson process. We consider four types of rate function for the Poisson process: power law, Musa-Okumoto, Goel-Okumoto, and a generalized Goel-Okumoto rate function. We also assume that a change-point may or may not be present. The analysis of the problem is performed by using a Bayesian approach via Markov chain Monte Carlo methods. The best model is chosen using the DIC criterion as well as graphical approach.

show abstract

“…In pre/post study designs, interventions are implemented for changing the rate of occurrence . The change in the rate of occurrence due to RTM may be erroneously attributed to the intervention.…”

Section: Introductionmentioning

confidence: 99%

Quantifying the regression to the mean effect in Poisson processes

Khan

Olivier

2018

Statistics in Medicine

View full text Add to dashboard Cite

Regression to the mean (RTM) can occur whenever an extreme observation is selected from a population and a later observation is closer to the population mean. A consequence of this phenomenon is that natural variability can be mistaken as real change. Simple expressions are available to quantify RTM when the underlying distribution is bivariate normal. However, there are many real-world situations, which are better approximated as a Poisson process. Examples include the number of hard disk failures during a year, the number of cargo ships damaged by waves, daily homicide counts in California, and the number of deaths per quarter attributable to acquired immune deficiency syndrome in Australia. In this paper, we derive expressions for quantifying RTM effects for the bivariate Poisson distribution for both the homogeneous and inhomogeneous cases. Statistical properties of our derivations have been evaluated through a simulation study. The asymptotic distributions of RTM estimators have been derived. The RTM effect for the number of people killed in road accidents in different regions of New South Wales (Australia) is estimated using maximum likelihood.

show abstract

On Modeling Change Points in Non-Homogeneous Poisson Processes

Abstract: Bayesian inference, power law process, Markov-chain Monte Carlo methods, change points,

Cited by 31 publications

References 14 publications

Analyzing the Relationships between some Parameters of Web Services Reputation

Analyzing the Relationships between some Parameters of Web Services Reputation

Non-homogeneous Poisson models with a change-point: an application to ozone peaks in Mexico city

Quantifying the regression to the mean effect in Poisson processes

Contact Info

Product

Resources

About