Login

Zaher Jaafar Khraibani

Assistant professor
Computer Science - Statistics department - Section I - Hadath
Speciality: Applied Mathematics
Specific Speciality: Statistics

Positions
- present :

Université Libanaise-Faculté des Sciences-Section 1
Hadat-Mont Liban

Teaching 5 Taught Courses
(2014-2015) ACTU 420 - *

M Mathematics for Finance and Actuarial Sciences

(2014-2015) MMAP 510 - Extreme Values and Point Process

M2 Biostatistics

(2014-2015) MMAP 524 - Credit Risk and Scoring

M2 Biostatistics

(2014-2015) Stat 426 - Clinical and epidemiological research methodology

M1 Statistics

(2014-2015) Stat 278 - Statistics I (statistics and probability)

BS Chemistry

Education
2005 - 2008: PHD

Université Paris 11
Biostatistique

2004 - 2005: Master 2

Université Montpellier II
Biostatistique

2003 - 2004: Maitrise

Université Libanaise
Statistique

Publications 15 publications
Anis Samir Hoayek,Gilles R. Ducharme,Zaher Khraibani Distribution-free inference in record series Extremes 2017

Let {Xt, t = 1} be a time series. A (upper) record is a value Xj such that Xj> max{X1,…,Xj-1}. Some popular models in record theory are the Yang-Nevzorov and the Linear Drift models. The stochastic behavior of records under these models has been much studied and many interesting distribution-free properties have been unearthed. However the estimation of the parameters of these models has been less explored. This work introduces some estimators of these parameters. Their behavior is investigated theoretically and by numerical simulations. It is shown that some of these estimators are easy to compute and their asymptotic properties are accurate and distribution-free. Some goodness-of-fit tests for these models are also presented.

Hussein Khraibani,Zaher Khraibani MODELLING DEPENDENCY STRUCTURAL OF THE WIND ENERGY IN LEBANON International Journal of Development Research 2017

For several decades, wind power is experiencing tremendous growth, however, the production of wind energy depends on wind intensity, strongly volatile, and is therefore characterized by a high degree of uncertainty. Planning the installation of a wind farm for several stations requires the assessment of the risk which in turn results in an assessment of the variability in production. Longevity, it starts with the recognition of the links between the various stations. The objective of this article is to develop a dependency structure assessment approach between different stations in Lebanon. The database used includes daily subsistence wind speeds of fourteen stations in Lebanon over a period of 6 years, from October 28th, 2009 until March 15th, 2016 and freely available on the NOAA network of American government. This database are used to estimate the necessary models such as, the univariate time series which will be modeled by the ARIMA process. We will establish a structure of spatial dependence of the innovations of these processes between different stations by using the copulas theory.

Anis Samir Hoayek,Gilles R. Ducharme,Zaher Khraibani,Zeineddine Hassan Estimation des paramètres pour des modèles adaptés aux séries de records (JdS2016) 2016

Soit X 1 , ..., X n une suite de variables aléatoires. Le record (supérieur) dans cette suite est la valeur M n telle que M n = max (X 1 ,. .. , X n). Un des modèles populaires en théorie de records est le Linear Drift Model (LDM), qui suppose que X n = Y n + cn, où c est le paramètre de dérive. Ce modèle a été étudié sur le plan probabiliste où on lui a trouvé de nombreuses propriétés intéressantes. Mais sur le plan statistique, peu de travaux ont porté sur l'estimation du paramètre c et le comportement de cet estimateur. Le but de ce travail est de présenter quelques estimateurs de ce paramètre de dérive et d'étudier leur comportement an de produire des énoncés d'inférence statistique dont les risques d'erreur sont quantiés avec une bonne précision. Mots-clés. Record, LDM, Estimateurs, Inférence statistique. Abstract. Let X 1 , ..., X n a sequence of random variables. In such a time series, a record (upper) is the value M n such that M n = max (X 1 ,. .. , X n). One of the popular models in record theory is the Linear Drift Model (LDM), which assumes that X n = Y n + cn, where c is the drift parameter. This model has been studied on probabilistic level where we found many interesting properties. But statistically, little work has been done on the estimation of the parameter c and the behavior of this estimator. The aim of this work is to present some estimators of the parameter c and to study their behavior in order to produce statements of statistical inference where the risks of error are accurately calculated. Estimation des paramètres pour des modèles adaptés aux séries de records. Available from: https://www.researchgate.net/publication/313600675_Estimation_des_parametres_pour_des_modeles_adaptes_aux_series_de_records [accessed May 22, 2017].

Zaher khraibani,Hussein Khraibani Self-Exciting Point Process to Study the Evolution of the Attack Terrorism International Journal of Statistics and Applications 2016

The terrorism attack became the first security world problem in the 21st century which the most terrorist attacks threaten civilians. The aim objective of this article is to develop the self-exciting point process to show that the terrorist attacks often follow a general pattern that can be modeled to study the evolution of the terrorism attack by using a statistical model especially the Hawkes process. The basic idea of this process is that the some events don’t occur independently; when a certain event happens. This model is a unique statistical model in literature which it is a special class of point process where the background rate is non-stationary.

Hussein M. Badran, Zaher Khraibani, Hussein Khraibani, Hassan Zeineddine, Aline Mefleh, Hassan Hamie Dependency Modelling of Natural Rare Phenomena: Application on Oil Rigs International Journal of Probability and Statistics 2016

Recently, the East Mediterranean region witnessed frequent extreme climate change conidtions manifested in high waves, strong wind and seismic activity. This resulted in increased attention to the safety of existing oil rigs. Thus, based on the variable dependency of the extreme value theory, the study aims to propose a new method to control the effect of climate conditions, particularly the wind speed, which may inflict structural damage to oil rigs. Additionally, the study seeks to compare the extreme value dependence between two different regions in Lebanon in order to evaluate how oil rigs, which will be installed in Lebanon’s maritime area, resist to high wind speed.

Zaher KHRAIBANI, Hussein KHRAIBANI, Hussein M. BADRAN, Sara SAFEIDDINE Statistical Methods for the Surveillance of Leishmanias in Lebanon: a time-series prediction International Journal of Advanced Scientific and Technical Research 2016

Leishmaniasis is a genuine public health problem in the countries of the Mediterranean region and more recently, in Lebanon. Therefore, prediction of and early warning for epidemics remains a research priority for control programs all over the world for Leishmaniasis, in the absence of an effective vaccination in Lebanon. We study in this article the surveillance of temporal distributions of events; such as the emergence of a declared disease with an increased incidence. The principal objective of this article is to show health surveillance statistical methods that detect the emergence of a disease and predict its future in order to take the necessary precautions to prevent and eliminate the consequences of emerging diseases.

Zaher Khraibani,Christine Jacob,Christian Ducrot, Carole Sala A Non Parametric Exact Test Based on the Number of Records for an Early Detection of Emerging Events: Illustration in Epidemiology Communication in Statistics- Theory and Methods 44(4) · February 2015 2015

Facing the first times of occurrence of events of a new type, such as seismic events, arrivals of individuals of a unknown species, occurrences of cases of a new disease, etc., it is crucial to predict if these events are only “sporadic,” or if they announce an emerging phenomenon (earthquake, emergence of a population, epidemic). We propose here an exact non parametric test statistic based on the number of lower records Nn in {ΔTk}1 k n , ΔTk being the waiting time between two successive events. Under H 0 (sporadic events), the {ΔTk} are assumed i.i.d., while under H 1 (emergent events), the {ΔTk} are assumed independent with cdf’s (cumulative distributions functions) {Gk} increasing with k. Under H 0, the distribution of Nn is independent of Gk, thus allowing a non parametric test of H 0. To calculate the power of the test under the alternative hypothesis H 1, we assume the particular family of cdf, , , where G is a continuous cdf on (0, ∞) and a > 1. These distributions represent an exponential occurrence rate of events. We show that the distribution of Nn under H 1 depends only on a (and not on G). We estimate a by the maximum likelihood estimator, and give the asymptotic properties of this estimator, as n → ∞. Finally, we illustrate the test on simulations and then on data concerning the atypical bovine spongiform encephalopathy in France.

Zaher Khraibani, Zainab Assaghir,, Hussein Khraibani, Dimitris Poursanidis, Anis Hoayek, Ghazi Bitar, Hassan Zeineddine, Argyro Zenetos and Hussein Badran. Application of The Records Method to Identify The Sporadicity of Percnon Gibbesi Distribution in Greece Journal of Scientific Research & Reports 2014

Zaher Khraibani, Christine Jacob, Christian Ducrot, Myriam Charras-Garrido & Carole Sala A nonparametric exact test based on the number of records for an early detection of emerging events.Illustration in epidemiology Communications in Statistics - Theory and Methods 2014

Khraibani, Z.; Badran, H. M.; Khraibani, H. Record method for the disasters natural Application to the Storm events Journal of Environmental Science & Engineering, Vol. 5 Issue 5, p643 2011

Christine Jacob, Zaher Khraibani, Elisaveta Pancheva Early detection of emergent events based on an extremal process approach Pliska 2009

Zaher Khraibani Emergence risk of the pathology in population 2008

Khraibani Z., Jacob C., Ducrot C., GARRIDO M. Early detection of an emerging disease based on records Technical Report 2008, UR 341, UR 346, Unity of Animal Epidemiology, INRA, F-63122 Saint Genès Champanelle, France, 27pp 2008

Ch. Jacob , Z.Khraibani , E.Pancheva An Extremal Process Approach for Sporadic Events XII-th Internationnal Summer Conference on Probability and Statistics (ISCPS). 2008

Myriam GARRIDO, Zaher KHRAIBANI, Christine JACOB, Christian DUCROT Emerging plant, animal and human diseases : strategies and study methods. 978-2-7592-0510-3 Release : 08/12/2010 éditeur "Quae." 2007

Modélisation Statistique des évènements rares : le cas des valeurs extrêmes et de l'étude des émergence

Supervision 5 Supervised Students
Modeling external events. Application to oil rigs

Aline Elias Mefleh
Master M2 Thesis: Actuarial Sciences in 2015

Estimation des paramètres pour des modèles adaptés aux séries de records.

Anis HOYAEK
Université de Montpellier- INSTITUT MONTPELLIÉRAIN ALEXANDER GROTHENDIECK Thèse Soutenue en 2016 sous la responsabilité de : Gilles Ducharme (Directeur) Hassan Zeineddine (Directeur) Zaher Khraibani (CoDirecteur)

Phénomènes de dépendance dans les extrêmes. Application à des plates-formes pétrolières

Aline MEFLEH
Laboratoire de Mathématiques Université de Franche-Comté These-COTUTELLE en cours sous la direction Romain Biard /Clément Dombry / Zaher Khraibani (Liban)

Applications des algorithmes stochastiques pour construire des estimateurs récursifs du nombre de clusters et de la position des nouveaux sommets avec appplication dans le domaine médicale.

Abir El Haj
Laboratoire de Mathématiques et Applications (LMA)-Université de Poitiers.Thèse en cours de préparation Sous la responsabilité de : Pierre-Yves Louis (CoDirecteur) Yousri Slaoui (Directeur) Zaher Khraibani (CoDirecteur)

Optimisation d'une infrastructure de données géo-spatiales pour les politiques publiques et le développement régional

Chadi Jabbour
Thèses en préparation à Montpellier en cotutelle avec l'Université libanaise , dans le cadre de École doctorale Economie Gestion de Montpellier (2015-.... ; Montpellier) , en partenariat avec LAMETA - Laboratoire Montpelliérain d'Economie Théorique et Appliquée (laboratoire) depuis le 03-10-2016 . Sous la direction de Jean-Michel Salles et de Latifa Ghalayini et Zaher Khraibani (Université libanaise).

Projet de thèse en Sciences Économiques. L'objectif de cette thèse est d'évaluer l'impact économique de l'information issue d'une infrastructure de télédétection. L'hypothèse est que la mise à disposition gratuite d'informations satellitaires pour les organismes de recherche et les services publics, renforce l'accès à ce type de données, et génère des économies de mutualisation et des gains significatifs en termes de productivité pour les services publics au niveau de l'efficacité, la visibilité et la transparence des politiques publiques. Avec le développement de l'information géographique, l'intégration, la mutualisation, puis l'interopérabilité des données et enfin la standardisation des produits ainsi générés sont devenus des questions centrales. L'enjeu est de garantir les conditions et les moyens de l'intégration d'informations géographiques issues de sources multiples. La création d'Infrastructures de Données Géographiques (ou Géo-spatiales IDGS) veut répondre à ces besoins (Crompvoets, 2006). Par leur action de mutualisation, d'accompagnement, de mise en réseau, de prétraitements et d'appui à l'apprentissage, les IDGS ont permis un développement significatif de l'information géographique et la multiplication dans des domaines très divers de produits et de services mobilisant ces informations. On observe notamment une croissance très importante de l'usage de produits et services issus de la télédétection, d'une part, pour le suivi de l'occupation des sols et les opérations d'aménagement des territoires et, d'autre part, pour des tâches spécifiques telles que l'évaluation des dommages post catastrophes ou le contrôle de la mise en œuvre de certaines politiques.

Languages
English

Limited working proficiency

French

Full professional proficiency