38 results on '"Ribatet, M."'
Search Results
2. Statistical Modeling of Spatial Extremes
- Author
-
Davison, A. C., Padoan, S. A., and Ribatet, M.
- Subjects
Statistics - Methodology - Abstract
The areal modeling of the extremes of a natural process such as rainfall or temperature is important in environmental statistics; for example, understanding extreme areal rainfall is crucial in flood protection. This article reviews recent progress in the statistical modeling of spatial extremes, starting with sketches of the necessary elements of extreme value statistics and geostatistics. The main types of statistical models thus far proposed, based on latent variables, on copulas and on spatial max-stable processes, are described and then are compared by application to a data set on rainfall in Switzerland. Whereas latent variable modeling allows a better fit to marginal distributions, it fits the joint distributions of extremes poorly, so appropriately-chosen copula or max-stable models seem essential for successful spatial modeling of extremes., Comment: Published in at http://dx.doi.org/10.1214/11-STS376 the Statistical Science (http://www.imstat.org/sts/) by the Institute of Mathematical Statistics (http://www.imstat.org)
- Published
- 2012
- Full Text
- View/download PDF
3. Comparing the spatial attractiveness of hospitals using zero-inflated spatial models
- Author
-
Saley, I., Molinari, N., and Ribatet, M.
- Published
- 2018
- Full Text
- View/download PDF
4. Conditional simulation of max-stable processes
- Author
-
DOMBRY, C., ÉYI-MINKO, F., and RIBATET, M.
- Published
- 2013
5. Rejoinder
- Author
-
Davison, A. C., Padoan, S. A., and Ribatet, M.
- Published
- 2012
6. Likelihood-Based Inference for Max-Stable Processes
- Author
-
Padoan, S. A., Ribatet, M., and Sisson, S. A.
- Published
- 2010
7. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes: Part 2 — The effects of the El Nino/Southern Oscillation, volcanic eruptions and contributions of atmo
- Author
-
Rieder H. E., Frossard L., Ribatet M., Staehelin J., Maeder J. A., Rocco S. D., Davison A. C., and Peter T.
- Abstract
We present the first spatial analysis of "fingerprints" of the El Niño/Southern Oscillation (ENSO) and atmospheric aerosol load after major volcanic eruptions (El Chichón and Mt. Pinatubo) in extreme low and high (termed ELOs and EHOs respectively) and mean values of total ozone for the northern and southern mid latitudes (defined as the region between 30° and 60° north and south respectively). Significant influence on ozone extremes was found for the warm ENSO phase in both hemispheres during spring especially towards low latitudes indicating the enhanced ozone transport from the tropics to the extra tropics. Further the results confirm findings of recent work on the connection between the ENSO phase and the strength and extent of the southern ozone "collar". For the volcanic eruptions the analysis confirms findings of earlier studies for the northern mid latitudes and gives new insights for the Southern Hemisphere. The results provide evidence that the negative effect of the eruption of El Chichón might be partly compensated by a strong warm ENSO phase in 1982–1983 at southern mid latitudes. The strong west east gradient in the coefficient estimates for the Mt. Pinatubo eruption and the analysis of the relationship between the AAO and ENSO phase the extent and the position of the southern ozone "collar" and the polar vortex structure provide clear evidence for a dynamical "masking" of the volcanic signal at southern mid latitudes. The paper also analyses the contribution of atmospheric dynamics and chemistry to long term total ozone changes. Here quite heterogeneous results have been found on spatial scales. In general the results show that EESC and the 11 yr solar cycle can be identified as major contributors to long term ozone changes. However a strong contribution of dynamical features (El Niño/Southern Oscillation (ENSO) North Atlantic Oscillation (NAO) Antarctic Oscillation (AAO) Quasi Biennial Oscillation (QBO)) to ozone variability and trends is found at a regional level. For the QBO (at 30 and 50 hPa) strong influence on total ozone variability and trends is found over large parts of the northern and southern mid latitudes especially towards equatorial latitudes. Strong influence of ENSO is found over the Northern and Southern Pacific Central Europe and central southern mid latitudes. For the NAO strong influence on column ozone is found over Labrador/Greenland the Eastern United States the Euro Atlantic Sector and Central Europe. For the NAO's southern counterpart the AAO strong influence on ozone variability and long term changes is found at lower southern mid latitudes including the southern parts of South America and the Antarctic Peninsula and central southern mid latitudes.
- Published
- 2013
- Full Text
- View/download PDF
8. Statistical modelling of spatial extremes (with Discussion)
- Author
-
Davison A. C., Padoan S., and Ribatet M.
- Abstract
The areal modelling of the extremes of a natural process such as rainfall or temperature is important in environmental statistics; for example understanding extreme areal rainfall is crucial in flood protection. This article reviews recent progress in the statistical modelling of spatial extremes starting with sketches of the necessary elements of extreme value statistics and geostatistics. The main types of statistical models thus far proposed based on latent variables on copulas and on spatial max stable processes are described and then are compared by application to a dataset on rainfall in Switzerland. Whereas latent variable modelling allows a better fit to marginal distributions it fits the joint distributions of extremes poorly so appropriately chosen copula or max stable models seem essential for successful spatial modelling of extemes.
- Published
- 2012
9. MEASURING EFFECT OF DISTANCE ON PROBABILITY OF CHOOSING HOSPITAL BY PATIENTS
- Author
-
Saley, I., primary, Molinari, N., additional, and Ribatet, M., additional
- Published
- 2016
- Full Text
- View/download PDF
10. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes Part 2
- Author
-
Rieder, Harald, Frossard, L., Ribatet, M., Staehelin, J., Maeder, J. A., Di Rocco, S., Davison, A. C., Peter, T., Weihs, P., and Holawe, F.
- Subjects
Atmospheric chemistry ,Meteorology ,Atmosphere - Abstract
We present the first spatial analysis of "fingerprints" of the El Nino/Southern Oscillation (ENSO) and atmospheric aerosol load after major volcanic eruptions (El Chichon and Mt. Pinatubo) in extreme low and high (termed ELOs and EHOs, respectively) and mean values of total ozone for the northern and southern mid-latitudes (defined as the region between 30 degrees and 60 degrees north and south, respectively). Significant influence on ozone extremes was found for the warm ENSO phase in both hemispheres during spring, especially towards low latitudes, indicating the enhanced ozone transport from the tropics to the extra-tropics. Further, the results confirm findings of recent work on the connection between the ENSO phase and the strength and extent of the southern ozone "collar". For the volcanic eruptions the analysis confirms findings of earlier studies for the northern mid-latitudes and gives new insights for the Southern Hemisphere. The results provide evidence that the negative effect of the eruption of El Chichon might be partly compensated by a strong warm ENSO phase in 1982–1983 at southern mid-latitudes. The strong west-east gradient in the coefficient estimates for the Mt. Pinatubo eruption and the analysis of the relationship between the AAO and ENSO phase, the extent and the position of the southern ozone "collar" and the polar vortex structure provide clear evidence for a dynamical "masking" of the volcanic signal at southern mid-latitudes. The paper also analyses the contribution of atmospheric dynamics and chemistry to long-term total ozone changes. Here, quite heterogeneous results have been found on spatial scales. In general the results show that EESC and the 11-yr solar cycle can be identified as major contributors to long-term ozone changes. However, a strong contribution of dynamical features (El Nino/Southern Oscillation (ENSO), North Atlantic Oscillation (NAO), Antarctic Oscillation (AAO), Quasi-Biennial Oscillation (QBO)) to ozone variability and trends is found at a regional level. For the QBO (at 30 and 50 hPa), strong influence on total ozone variability and trends is found over large parts of the northern and southern mid-latitudes, especially towards equatorial latitudes. Strong influence of ENSO is found over the Northern and Southern Pacific, Central Europe and central southern mid-latitudes. For the NAO, strong influence on column ozone is found over Labrador/Greenland, the Eastern United States, the Euro-Atlantic Sector, and Central Europe. For the NAO's southern counterpart, the AAO, strong influence on ozone variability and long-term changes is found at lower southern mid-latitudes, including the southern parts of South America and the Antarctic Peninsula, and central southern mid-latitudes.
- Published
- 2013
- Full Text
- View/download PDF
11. Modeling All Exceedances Above a Threshold Using an Extremal Dependence Structure: Inferences on Several Flood Characteristics
- Author
-
Ribatet, M., Ouarda, T.B., Sauquet, E., Gresillon, J.M., Hydrologie-Hydraulique (UR HHLY), Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA), and Institut National de la Recherche Scientifique [Québec] (INRS)
- Subjects
FREQUENCE ,MULTIVARIATE EXTREME VALUE DISTRIBUTION ,EXTREMAL INDEX ,Statistics ,Events ,STATISTIQUE ,Values ,Independence ,MODELISATION ,MARKOV CHAIN MODELS ,Frequency-Analysis ,Duration ,[SDE]Environmental Sciences ,Markov-Chain Models ,Distributions ,PROCESSUS DE MARKOV ,CRUE ,FLOOD FREQUENCY ANALYSIS ,SEUIL - Abstract
Flood quantile estimation is of great importance for several types of engineering studies and policy decisions. However, practitioners must often deal with the limited availability of data and with short-length observation series. Thus, the information must be used optimally. During the last decades, to make better use of available data, inferential methodology has evolved from annual maxima modeling to peaks over a threshold. To mitigate the lack of data, peaks over a threshold are sometimes combined with additional information, mostly regional or historical information. However, the most important information for the practitioner remains the data available at the target site. In this study, a model that allows inference on the whole time series is introduced. In particular, the proposed model takes into account the dependence between successive extreme observations using an appropriate extremal dependence structure. Results show that this model leads to more accurate flood peak quantile estimates than conventional estimators. In addition, as the time dependence is taken into account, inferences on other flood characteristics can be performed. An illustration is given with flood duration data. Our analysis shows that the accuracy of the proposed models to estimate flood duration is related to specific catchment characteristics. Some suggestions to increase the flood duration predictions are presented.
- Published
- 2009
12. Consolidation de l'information hydrologique disponible localement et régionalement pour l'estimation probabiliste du régime des crues
- Author
-
Ribatet, M., Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), Institut polytechnique de Grenoble - Grenoble Institute of Technology (Grenoble INP ), and Doctorat INP Grenoble et PhD de l'Institut National de la Recherche Scientifique, Québec, CAN
- Subjects
CEMAGREF ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences ,thesis ,thèse - Abstract
To define the design flood, practitioners must often deal with only few data available. The aim of this work was to propose new classes of probabilistic models that are more accurate for this kind of applications. In this perspective, we propose three different models: two regional approaches and a fully local one. Unlike fully local models, the regional approaches include information from other gauging stations. Our results show that the proposed regional Bayesian estimators are more robust to the discordancy degree of the sites within the region. In addition, for larger quantile estimation (T >= 50 years), the concept of a regional parameter which controls the tail behaviour seems to be relevant. However, this concept has to be proposed and not imposed within the likelihood function.It is overwhelmingly clear that the most important information one disposes is the target site one. To this aim, we propose a third model that is fully local, i.e., which only uses the latest recorded data. This new model is innovative as the whole time series is involved in the estimation procedure; not only cluster maxima. Consequently, even with only a five years record length time series, the sample size becomes large. Our results show that, for flood quantile estimations, this model clearly outperforms the estimators conventionally used in hydrology. Furthermore, by definition, this model allows inferences on flood dynamics; Le praticien, lors de l'étape de prédétermination des débits de crue, est souvent confronté à un jeu de données restreint. Dans notre travail de recherche, nous avons proposé trois nouveaux modèles probabilistes spécialement conçus pour l'estimation des caractéristiques du régime des crues en contexte partiellement jaugé. Parmi ces modèles, deux d'entre eux sont des modèles dits régionaux, i.e. intégrant de l'information en provenance de stations ayant un comportement réputé similaire à celui du site étudié. Ces modèles, basés sur la théorie Bayésienne, ont montré une grande robustesse au degré d'hétérogénéité des sites appartenant à la région. De même, il est apparu que pour l'estimation des forts quantiles (T >= 50 ans), l'idée d'un paramètre régional contrôlant l'extrapolation est pertinente mais doit d'être intégrée de manière souple et non imposée au sein de la vraisemblance. L'information la plus précieuse dont le praticien dispose étant celle en provenance du site d'étude, le troisième modèle proposé revient sur l'estimation à partir des seules données contemporaines au site d'étude. Ce nouveau modèle utilise une information plus riche que celle issue d'un échantillonnage classique de v.a.i.id. maximales puisque toute la chronique est exploitée. Dès lors, même avec seulement cinq années d'enregistrement et grâce à une modélisation de la dépendance entres les observations successives, la taille des échantillons exploités est alors bien plus importante. Nous avons montré que pour l'estimation des quantiles de crues, ce modèle surpasse très nettement les approches locales classiquement utilisées en hydrologie. Ce résultat est d'autant plus vrai lorsque les périodes de retour deviennent importantes. Enfin, part construction, cette approche permet également d'obtenir une estimation probabiliste de la dynamique des crues.
- Published
- 2007
13. POT : modélisation des excès supérieurs à un seuil
- Author
-
Ribatet, M. and Irstea Publications, Migration
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,CODE DEVELOPMENT ,HHLY ,HHLYHYD ,GPD ,INFERENCE - Abstract
The Generalised Pareto Distribution (GPD) is the limiting distribution of normalised excesses over a threshold, as the threshold approaches the endpoint of the variable (Pickands, 1975). The POT package contains useful tools to perform statistical analysis for peaks over a threshold using the GPD approximation. There is many packages devoted to the extreme value theory (evd, ismev, evir,...); however, the POT package is specialised in peaks over threshold analysis. Moreover, this is currently the only one which proposes many estimators for the GPD. A user's guide (as a package vignette) and two demos are also included in the package.
- Published
- 2007
14. Bayesian priors based on regional information: application to regional flood frequency analysis
- Author
-
Ribatet, M., Sauquet, Eric, Gresillon, J.M., Ouarda, T.B., Irstea Publications, Migration, Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), INRS EAU QUEBEC CAN, Partenaires IRSTEA, and Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA)-Institut national de recherche en sciences et technologies pour l'environnement et l'agriculture (IRSTEA)
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,MCMC ,BAYESIAN INFERENCE ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences ,REGIONAL FREQUENCY ANALYSIS ,INDEX FLOOD - Abstract
Extrait de document; Flood Frequency Analysis is usually based on the fitting of an extreme value distribution to the series of local stream flow. However, when the at-site time-series is short, frequency analysis results become unreliable. In this work, a regional Bayesian model to estimate flood quantile from a few years of stream flow data is proposed. This model is less restrictive than the Index Flood model while preserving the formalism of homogeneous regions. Performance of the proposed model is assessed on a set of French gauging stations. The accuracy of quantile estimates as a function of homogeneousness level of the pooling group is also analyzed. Results indicate that the regional Bayesian model outperforms the Index Flood model and local estimators. Furthermore, it seems that working with relatively large and homogeneous regions may lead to more accurate results than working with smaller and highly homogeneous regions.
- Published
- 2006
15. Analyse de sensibilité globale de modèles numériques à paramètres incontrôlables
- Author
-
Iooss, Bertrand, Ribatet, M., Commissariat à l'énergie atomique et aux énergies alternatives (CEA), Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), and Irstea Publications, Migration
- Subjects
[SDE] Environmental Sciences ,CEA ,CEMAGREF ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences ,SURFACE DE REPONSE ,GLM ,MODELE JOINT - Abstract
[Departement_IRSTEA]RE [TR1_IRSTEA]RIE / TRANSFEAU; L'analyse de sensibilité globale permet de quantifier l'influence des différents paramètres d'entrée incertains sur la variabilité de la réponse d'un modèle numérique. Les méthodes quantitatives sont applicables aux codes de calcul déterministes (pour lesquels un même jeu de paramètres d'entrée procure toujours la même réponse). Ce papier propose une méthode d'analyse de sensibilité globale quand le code de calcul est stochastique (possédant une variabilité non contrôlée ou non quantifiée par un ou plusieurs paramètres d'entrée scalaires). Nous modélisons la moyenne et la dispersion des réponses du code par deux modèles linéaires généralisés (GLM) interdépendants. Le modèle de la moyenne permet d'obtenir les indices de sensibilité des paramètres contrôlables. Le modèle de la dispersion permet d'obtenir un indice de sensibilité regroupant les contributions de tous les paramètres non contrôlables.
- Published
- 2006
16. Procédures d'estimation bayésienne des quantiles de crues via une information régionale a priori
- Author
-
Ribatet, M., Sauquet, Eric, Irstea Publications, Migration, Hydrologie-Hydraulique (UR HHLY), and Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF)
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences - Abstract
Dans cette présentation, nous décrirons le modèle bayésien développé : modèle bayésien entièrement paramétrique avec information a priori établie à partir du modèle de l'indice de crue. Nous montrerons en quoi cette approche généralise le modèle de l'indice de crue et permet d'établir un modèle ayant une justification théorique. Enfin, nous ferons une comparaison des modèles locaux (estimation par Maximum de Vraisemblance, L-Moments, . . . ), de l'indice de crue et bayésien sur un jeu de données observées. Dans ce but, nous essaierons de montrer la convergence plus rapide du modèle bayésien pour des échantillons de petites tailles, de même des caractéristiques telle la robustesse ou le biais seront évaluées afin de comparer le plus objectivement possible les différents modèles.
- Published
- 2005
17. Analyse Bayésienne, méthodes MCMC et copules: quelles applications en hydrologie?
- Author
-
Renard, Benjamin, Müller, A., Ribatet, M., Lang, M., Sauquet, Eric, Hydrologie-Hydraulique (UR HHLY), and Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF)
- Subjects
CEMAGREF ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences - Abstract
Cette présentation s'intéresse à la modélisation probabiliste des évènements hydrologiques, dont une application classique est l'analyse fréquentielle des évènements extrêmes, qui conduit au calcul de quantiles de crues ou de pluies, par exemple. Le schéma général d'une modélisation probabiliste peut être décrit comme suit : Création d'un échantillon de données, si possible iid (indépendant, identiquement distribué) üChoix d'une loi de probabilité pour décrire la distribution de ces données üEstimation des paramètres de cette loi Parmi les différentes méthodes d'estimation, l'analyse Bayésienne a gagné en popularité au cours des dernières années. Schématiquement, cette méthode consiste à baser l'estimation des paramètres sur une distribution nommée loi a posteriori, qui mélange l'information portée par les données (via la vraisemblance) et une information a priori exogène aux données (avis d'expert, informations régionales, contraintes physiques, ). Le formalisme Bayésien possède plusieurs avantages par rapport à une analyse classique. Tout d'abord, l'introduction de connaissances a priori est susceptible d'améliorer l'estimation des paramètres. Ce type de connaissances existe dans la grande majorité des cas : par exemple, il est possible d'utiliser les méthodes développées pour l'estimation des quantiles de crues sur des sites non jaugés (cf. programme PUB). De plus, le formalisme Bayésien permet une analyse complète des incertitudes : échantillonnage (c'est le cas également des analyses classiques), mais aussi de modélisation (quelle loi de probabilité choisir ? modéliser une tendance linéaire, exponentielle, quadratique ?), ou de métrologie (prise en compte de l'incertitude liée à l'extrapolation des courbes de tarage, ou à la reconstitution de données historiques). Enfin, en basant l'inférence sur une loi de probabilité, le calcul des intervalles de confiance est très naturel, et ne repose sur aucune hypothèse asymptotique. Cependant, certains inconvénients demeurent : tout d'abord, la traduction de connaissances a priori en une loi de probabilité sur les paramètres est loin d'être triviale. De plus, la loi a posteriori s'exprime en général comme une distribution multivariée qui est délicate à manipuler dès que le nombre de paramètres est supérieur à deux ou trois. Cette difficulté explique pourquoi l'utilisation de l'analyse Bayésienne est assez récente dans le domaine des valeurs extrêmes, alors que certains hydrologues utilisent déjà ce formalisme depuis les années 60 (cf. les travaux de J. Bernier), dans le cadre de lois Gaussiennes plus simples à manipuler. Les méthodes dites MCMC (Monte Carlo Markov Chain) fournissent une solution algorithmique à ce problème, mais nécessitent une puissance informatique qui n'était pas disponible il y a encore quelques dizaines d'années. Dans cet exposé, nous présenterons brièvement le principe de ces méthodes, qui présentent l'avantage d'être utilisables même avec un « grand » nombre de paramètres (quelques dizaines). L'apport de l'analyse Bayésienne et des méthodes MCMC en hydrologie sera ensuite illustré par des cas d'études relatifs à l'estimation des quantiles de crues. Tout d'abord, nous verrons comment inclure des connaissances exogènes aux données, via une distribution a priori. Ces connaissances peuvent être issues d'une certaine expertise de l'hydrologue, ou peuvent dériver de connaissances physiques. Il est également possible d'inclure de manière très naturelle des informations régionales dans cette distribution a priori (cf. thèse de M. Ribatet). Nous illustrerons ensuite comment mélanger différents modèles, ce qui permettra de prendre en compte au moins partiellement l'incertitude liée au choix du modèle. L'application concernera ici la modélisation d'une tendance temporelle sur les paramètres de la distribution des crues. Un des problèmes est lié au fait que plusieurs tendances peuvent s'ajuster de manière équivalente aux données, mais peuvent diverger lorsque l'on cherche à extrapoler ces évolutions dans le futur. Ne considérer qu'un unique modèle peut alors entraîner une forte sous-estimation des intervalles de confiance futurs. La troisième application concerne les modèles impliquant l'estimation d'un grand nombre de paramètres. De tels modèles résultent souvent d'une vision multivariée des phénomènes (évaluation multi-durée des pluies ou des débits, caractérisation pointe-volume-durée d'une crue, phénomènes spatialisés). Deux grandes difficultés empêchent d'effectuer ce type d'analyse de manière totalement rigoureuse. La première est liée au nombre de paramètres à estimer, ce qui empêche d'utiliser des méthodes classiques de type Newton pour la maximisation de la vraisemblance. Des méthodes alternatives sont en général développées, mais elles reposent souvent sur des hypothèses fortes, qui conduisent à une sous estimation des incertitudes. Nous verrons donc comment les outils MCMC peuvent être utiles pour estimer proprement un nombre modérément élevé de paramètres. Le cas d'étude présenté concernera l'estimation d'une tendance régionale sur les débits de crues pour un ensemble de sites. Nous évoquerons également quelques applications potentielles à la méthode de l'indice de crue, ou à l'estimation de distributions multi-durées sur les pluies par exemple (cf. thèse de A. Muller). La seconde difficulté est d'ordre théorique, et est liée à la difficulté de modéliser des dépendances dans un cadre non-Gaussien. Ce domaine est toujours du domaine de la recherche en statistiques, et ne possède pas aujourd'hui de solution satisfaisante à la fois du point de vue théorique et du point de vue pratique. Cependant quelques solutions, faisant intervenir des hypothèses plus ou moins fortes, sont d'ores et déjà envisageables. En particulier, l'utilisation de copules permet de créer assez simplement des lois multivariées à partir des lois marginales souhaitées (des distributions des valeurs extrêmes, par exemple). Nous illustrerons brièvement le principe de ces outils, et présenterons quelques exemples d'application, concernant la significativité régionale d'un test répété sur plusieurs sites, ou la gestion du risque à une échelle régionale. L'intégration des progrès statistiques aux problématiques hydrologiques est indiscutablement un des moyens d'améliorer l'analyse fréquentielle des évènements extrêmes. L'analyse Bayésienne ou les outils MCMC sont souvent indispensables pour parvenir à intégrer ces améliorations. La première perspective consistera à évaluer comment l'utilisation combinée des outils MCMC et des copules peut améliorer la prise en compte de problèmes multivariés. Nous évoquerons également d'autres possibilités pour prendre en compte la dépendance entre valeurs extrêmes, notamment l'utilisation d'outils issus de la géostatistique, couplés avec des modèles Bayésiens.
- Published
- 2005
18. Bayesian analysis of the rainfall depth versus duration and frequences
- Author
-
Müller, A., Renard, Benjamin, Ribatet, M., Lang, M., Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), and Irstea Publications, Migration
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,HHLY ,HHLYHYD ,MARSEILLE ,[SDE]Environmental Sciences ,COURBES HAUTEUR DE PLUIE - DUREE - FREQUENCE ,ANALYSE MULTIVARIEE ,ALGORITHME MCMC - Abstract
To estimate the rainfall depth - duration - frequences, two models are presented, and fitted to a choice of data, in a bayesian framework. Different likelihoods are proposed for the multivariate data., Pour l'estimation des courbes de hauteurs de pluie-durée-fréquence, on présente deux modèles, que l'on ajuste à un choix de données, suivant une méthode bayésienne. Le choix de la vraisemblance impose ici une discussion sur le caractère multivarié des données.
- Published
- 2005
19. Bayesian estimation procedure for flood quantiles using a regional prior information
- Author
-
Ribatet, M., Sauquet, Eric, Irstea Publications, Migration, Hydrologie-Hydraulique (UR HHLY), and Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF)
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,HHLY ,HHLYHYD ,[SDE]Environmental Sciences - Abstract
Dans cette présentation, nous décrirons le modèle bayésien développé : modèle bayésien entièrement paramétrique avec information a priori établie à partir du modèle de l'indice de crue. Nous montrerons en quoi cette approche généralise le modèle de l'indice de crue et permet d'établir un modèle ayant une justification théorique. Enfin, nous ferons une comparaison des modèles locaux (estimation par Maximum de Vraisemblance, L-Moments, . . . ), de l'indice de crue et bayésien sur un jeu de données observées. Dans ce but, nous essaierons de montrer la convergence plus rapide du modèle bayésien pour des échantillons de petites tailles, de même des caractéristiques telle la robustesse ou le biais seront évaluées afin de comparer le plus objectivement possible les différents modèles.
- Published
- 2005
20. Modélisation bayésienne des courbes Hauteur de pluie-Durée-Fréquence
- Author
-
Müller, A., Renard, Benjamin, Ribatet, M., Lang, M., Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), and Irstea Publications, Migration
- Subjects
[SDE] Environmental Sciences ,CEMAGREF ,HHLY ,HHLYHYD ,MARSEILLE ,[SDE]Environmental Sciences ,COURBES HAUTEUR DE PLUIE - DUREE - FREQUENCE ,ANALYSE MULTIVARIEE ,ALGORITHME MCMC - Abstract
To estimate the rainfall depth - duration - frequences, two models are presented, and fitted to a choice of data, in a bayesian framework. Different likelihoods are proposed for the multivariate data., Pour l'estimation des courbes de hauteurs de pluie-durée-fréquence, on présente deux modèles, que l'on ajuste à un choix de données, suivant une méthode bayésienne. Le choix de la vraisemblance impose ici une discussion sur le caractère multivarié des données.
- Published
- 2005
21. Caractérisation du régime des hautes eaux en débit-durée-fréquence. Application en région Rhône-Alpes
- Author
-
Sauquet, Eric, Ribatet, M., Hydrologie-Hydraulique (UR HHLY), Centre national du machinisme agricole, du génie rural, des eaux et forêts (CEMAGREF), irstea, and Irstea Publications, Migration
- Subjects
[SDE] Environmental Sciences ,RHONE ALPES ,CRUPEDIX ,CEMAGREF ,HHLYHYD ,HHLY ,[SDE]Environmental Sciences - Abstract
The aim of this study is to carry out the Flood duration frequency (QdF) approach to an extended dataset of basins located in the Rhone-Alps Region. More than 30 gauging stations monitored by the Rhône-Alpes DIREN were analysed regarding to the stationarity. Hydrographs and peaks over thresholds for each of them were derived before applying the QdF approach. Basins were pooled and the index flood method was considered to regionalise flood characteristics in combination with the CRUPEDIX formula., Cette étude a pour objectif de réaliser une synthèse statistique du fonctionnement en crue des cours d'eau en Rhône-Alpes selon l`approche probabiliste QdF. Sur plus de 30 sites instrumentés par la DIREN Rhône-Alpes, une critique des mesures de débit a été menée avant d'extraire des échantillons de valeurs représentatives des crues et de leur appliquer la méthode QdF. L`analyse locale étant réalisée, des comportements types de bassins ont été identifiés avant de mettre en place une technique de régionalisation combinant la méthode de l`indice de crue et la formule empirique de CRUPEDIX.
- Published
- 2004
22. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes – Part 1: Statistical models and spatial fingerprints of atmospheric dynamics and chemistry
- Author
-
Frossard, L., primary, Rieder, H. E., additional, Ribatet, M., additional, Staehelin, J., additional, Maeder, J. A., additional, Di Rocco, S., additional, Davison, A. C., additional, and Peter, T., additional
- Published
- 2013
- Full Text
- View/download PDF
23. Conditional simulation of max-stable processes
- Author
-
Dombry, C., primary, Eyi-Minko, F., additional, and Ribatet, M., additional
- Published
- 2012
- Full Text
- View/download PDF
24. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes – Part 1: Statistical models and spatial fingerprints of atmospheric dynamics and chemistry
- Author
-
Frossard, L., primary, Rieder, H. E., additional, Ribatet, M., additional, Staehelin, J., additional, Maeder, J. A., additional, Di Rocco, S., additional, Davison, A. C., additional, and Peter, T., additional
- Published
- 2012
- Full Text
- View/download PDF
25. Supplementary material to "On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes – Part 2: The effects of the El Niño/Southern Oscillation, volcanic eruptions and contributions of atmospheric dynamics and chemistry to long-term total ozone changes"
- Author
-
Rieder, H. E., primary, Frossard, L., additional, Ribatet, M., additional, Staehelin, J., additional, Maeder, J. A., additional, Di Rocco, S., additional, Davison, A. C., additional, Peter, T., additional, Weihs, P., additional, and Holawe, F., additional
- Published
- 2012
- Full Text
- View/download PDF
26. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes – Part 2: The effects of the El Niño/Southern Oscillation, volcanic eruptions and contributions of atmospheric dynamics and chemistry to long-term total ozone changes
- Author
-
Rieder, H. E., primary, Frossard, L., additional, Ribatet, M., additional, Staehelin, J., additional, Maeder, J. A., additional, Di Rocco, S., additional, Davison, A. C., additional, Peter, T., additional, Weihs, P., additional, and Holawe, F., additional
- Published
- 2012
- Full Text
- View/download PDF
27. Extreme events in total ozone over Arosa – Part 1: Application of extreme value theory
- Author
-
Rieder, H. E., primary, Staehelin, J., additional, Maeder, J. A., additional, Peter, T., additional, Ribatet, M., additional, Davison, A. C., additional, Stübi, R., additional, Weihs, P., additional, and Holawe, F., additional
- Published
- 2010
- Full Text
- View/download PDF
28. Extreme events in total ozone over Arosa – Part 2: Fingerprints of atmospheric dynamics and chemistry and effects on mean values and long-term changes
- Author
-
Rieder, H. E., primary, Staehelin, J., additional, Maeder, J. A., additional, Peter, T., additional, Ribatet, M., additional, Davison, A. C., additional, Stübi, R., additional, Weihs, P., additional, and Holawe, F., additional
- Published
- 2010
- Full Text
- View/download PDF
29. Relationship between high daily erythemal UV doses, total ozone, surface albedo and cloudiness: An analysis of 30years of data from Switzerland and Austria
- Author
-
Rieder, H.E., primary, Staehelin, J., additional, Weihs, P., additional, Vuilleumier, L., additional, Maeder, J.A., additional, Holawe, F., additional, Blumthaler, M., additional, Lindfors, A., additional, Peter, T., additional, Simic, S., additional, Spichtinger, P., additional, Wagner, J.E., additional, Walker, D., additional, and Ribatet, M., additional
- Published
- 2010
- Full Text
- View/download PDF
30. Supplementary material to "Extreme events in total ozone over Arosa – Part 1: Application of extreme value theory"
- Author
-
Rieder, H. E., primary, Staehelin, J., additional, Maeder, J. A., additional, Peter, T., additional, Ribatet, M., additional, Davison, A. C., additional, Stübi, R., additional, Weihs, P., additional, and Holawe, F., additional
- Published
- 2010
- Full Text
- View/download PDF
31. Usefulness of the reversible jump Markov chain Monte Carlo model in regional flood frequency analysis
- Author
-
Ribatet, M., primary, Sauquet, E., additional, Grésillon, J. M., additional, and Ouarda, T. B. M. J., additional
- Published
- 2007
- Full Text
- View/download PDF
32. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes -- Part 1: Statistical models and spatial fingerprints of atmospheric dynamics and chemistry.
- Author
-
Frossard, L., Rieder, H. E., Ribatet, M., Staehelin, J., Maeder, J. A., Di Rocco, S., Davison, A. C., and Peter, T.
- Abstract
We use models for mean and extreme values of total column ozone on spatial scales to analyze "fingerprints" of atmospheric dynamics and chemistry on long-term ozone changes at northern and southern mid-latitudes. The r-largest order statistics method is used for pointwise analysis of extreme events in low and high total ozone (termed ELOs and EHOs, respectively). For the corresponding mean value analysis a pointwise autoregressive moving average model (ARMA) is used. The statistical models include important atmospheric covariates to describe the dynamical and chemical state of the atmosphere: the solar cycle, the Quasi-Biennial Oscillation (QBO), ozone depleting substances (ODS) in terms of equivalent effective stratospheric chlorine (EESC), the North Atlantic Oscillation (NAO), the Antarctic Oscillation (AAO), the El Niño/Southern Oscillation (ENSO), and aerosol load after the volcanic eruptions of El Chichón and Mt. Pinatubo. The influence of the individual covariates on mean and extreme levels in total column ozone is derived on a grid cell basis. The results show that "fingerprints", i.e., significant influence, of dynamical and chemical features are captured in both the "bulk" and the tails of the ozone distribution, respectively described by means and EHOs/ELOs. While results for the solar cycle, QBO and EESC are in good agreement with findings of earlier studies, unprecedented spatial fingerprints are retrieved for the dynamical covariates. [ABSTRACT FROM AUTHOR]
- Published
- 2012
- Full Text
- View/download PDF
33. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes -- Part 2: The effects of the El Niño/Southern Oscillation, volcanic eruptions and contributions of atmospheric dynamics and chemistry to long-term total ozone changes.
- Author
-
Rieder, H. E., Frossard, L., Ribatet, M., Staehelin, J., Maeder, J. A., Di Rocco, S., Davison, A. C., Peter, T., Weihs, P., and Holawe, F.
- Abstract
We present the first spatial analysis of "fingerprints" of the El Niño/Southern Oscillation (ENSO) and atmospheric aerosol load after major volcanic eruptions (El Chichón and Mt. Pinatubo) in extreme low and high (termed ELOs and EHOs, respectively) and mean values of total ozone for the northern and southern mid-latitudes (defined as the region between 30° and 60° north and south, respectively). Significant influence on ozone extremes was found for the warm ENSO phase in both hemispheres during spring, especially towards low latitudes, indicating the enhanced ozone transport from the tropics to the extra-tropics. Further, the results confirm findings of recent work on the connection between the ENSO phase and the strength and extent of the southern ozone "collar". For the volcanic eruptions the analysis confirms findings of earlier studies for the northern mid-latitudes and gives new insights for the Southern Hemisphere. The results provide evidence that the negative effect of the eruption of El Chichón might be partly compensated by a strong warm ENSO phase in 1982-83 at southern midlatitudes. The strong west-east gradient in the coefficient estimates for the Mt. Pinatubo eruption and the analysis of the relationship between the AAO and ENSO phase, the extent and the position of the southern ozone "collar" and the polar vortex structure provide clear evidence for a dynamical "masking" of the volcanic signal at southern mid-latitudes. The paper also analyses the contribution of atmospheric dynamics and chemistry to long-term total ozone changes. Here, quite heterogeneous results have been found on spatial scales. In general the results show that EESC and the 11-yr solar cycle can be identified as major contributors to long-term ozone changes. However, a strong contribution of dynamical features (El Niño/Southern Oscillation (ENSO), North Atlantic Oscillation (NAO), Antarctic Oscillation (AAO), Quasi-Biennial Oscillation (QBO)) to ozone variability and trends is found at a regional level. For the QBO (at 30 and 50 hPa), strong influence on total ozone variability and trends is found over large parts of the northern and southern mid-latitudes, especially towards equatorial latitudes. Strong influence of ENSO is found over the Northern and Southern Pacific, Central Europe and central southern mid-latitudes. For the NAO, strong influence on column ozone is found over Labrador/Greenland, the Eastern United States, the Euro-Atlantic Sector and Central Europe. For the NAO's southern counterpart, the AAO, strong influence on ozone variability and long-term changes is found at lower southern mid-latitudes, including the southern parts of South America and the Antarctic Penin- sula, and central southern mid-latitudes. [ABSTRACT FROM AUTHOR]
- Published
- 2012
- Full Text
- View/download PDF
34. On the relationship between total ozone and atmospheric dynamics and chemistry at mid-latitudes – Part 1: Statistical models and spatial fingerprints of atmospheric dynamics and chemistry
- Author
-
Frossard, L., Rieder, Harald, Ribatet, M., Staehelin, J., Maeder, J. A., Di Rocco, S., Davison, A. C., and Peter, T.
- Subjects
Atmospheric chemistry ,13. Climate action ,Atmosphere ,Statistics - Abstract
We use statistical models for mean and extreme values of total column ozone to analyze "fingerprints" of atmospheric dynamics and chemistry on long-term ozone changes at northern and southern mid-latitudes on grid cell basis. At each grid cell, the r-largest order statistics method is used for the analysis of extreme events in low and high total ozone (termed ELOs and EHOs, respectively), and an autoregressive moving average (ARMA) model is used for the corresponding mean value analysis. In order to describe the dynamical and chemical state of the atmosphere, the statistical models include important atmospheric covariates: the solar cycle, the Quasi-Biennial Oscillation (QBO), ozone depleting substances (ODS) in terms of equivalent effective stratospheric chlorine (EESC), the North Atlantic Oscillation (NAO), the Antarctic Oscillation (AAO), the El Niño/Southern Oscillation (ENSO), and aerosol load after the volcanic eruptions of El Chichón and Mt. Pinatubo. The influence of the individual covariates on mean and extreme levels in total column ozone is derived on a grid cell basis. The results show that "fingerprints", i.e., significant influence, of dynamical and chemical features are captured in both the "bulk" and the tails of the statistical distribution of ozone, respectively described by mean values and EHOs/ELOs. While results for the solar cycle, QBO, and EESC are in good agreement with findings of earlier studies, unprecedented spatial fingerprints are retrieved for the dynamical covariates. Column ozone is enhanced over Labrador/Greenland, the North Atlantic sector and over the Norwegian Sea, but is reduced over Europe, Russia and the Eastern United States during the positive NAO phase, and vice-versa during the negative phase. The NAO's southern counterpart, the AAO, strongly influences column ozone at lower southern mid-latitudes, including the southern parts of South America and the Antarctic Peninsula, and the central southern mid-latitudes. Results for both NAO and AAO confirm the importance of atmospheric dynamics for ozone variability and changes from local/regional to global scales.
35. Extreme events in total ozone over Arosa---Part 1: Application of extreme value theory
- Author
-
Rieder, H. E., Staehelin, J., Maeder, J. A., Peter, T., Ribatet, M., Davison, A. C., Stübi, R., Weihs, P., and Holawe, F.
- Subjects
Locally Weighted Regression ,Northern-Hemisphere ,Series - Abstract
In this study ideas from extreme value theory are for the first time applied in the field of stratospheric ozone research, because statistical analysis showed that previously used concepts assuming a Gaussian distribution (e.g. fixed deviations from mean values) of total ozone data do not adequately address the structure of the extremes. We show that statistical extreme value methods are appropriate to identify ozone extremes and to describe the tails of the Arosa (Switzerland) total ozone time series. In order to accommodate the seasonal cycle in total ozone, a daily moving threshold was determined and used, with tools from extreme value theory, to analyse the frequency of days with extreme low (termed ELOs) and high (termed EHOs) total ozone at Arosa. The analysis shows that the Generalized Pareto Distribution (GPD) provides an appropriate model for the frequency distribution of total ozone above or below a mathematically well-defined threshold, thus providing a statistical description of ELOs and EHOs. The results show an increase in ELOs and a decrease in EHOs during the last decades. The fitted model represents the tails of the total ozone data set with high accuracy over the entire range (including absolute monthly minima and maxima), and enables a precise computation of the frequency distribution of ozone mini-holes (using constant thresholds). Analyzing the tails instead of a small fraction of days below constant thresholds provides deeper insight into the time series properties. Fingerprints of dynamical (e.g. ENSO, NAO) and chemical features (e.g. strong polar vortex ozone loss), and major volcanic eruptions, can be identified in the observed frequency of extreme events throughout the time series. Overall the new approach to analysis of extremes provides more information on time series properties and variability than previous approaches that use only monthly averages and/or mini-holes and mini-highs.
36. Relationship between high daily erythemal UV doses, total ozone, surface albedo and cloudiness: An analysis of 30 years of data from Switzerland and Austria
- Author
-
Rieder, H. E., Staehelin, J., Weihs, P., Vuilleumier, L., Maeder, J. A., Holawe, F., Blumthaler, M., Lindfors, A., Peter, T., Simic, S., Spichtinger, P., Wagner, J. E., Walker, D., and Ribatet, M.
- Subjects
Surface albedo ,Clouds ,Total ozone ,UV radiation - Abstract
This work investigates the occurrence frequency of days with high erythemal UV doses at three stations in Switzerland and Austria (Davos, Hoher Sonnblick and Vienna) for the time period 1974-2003. While several earlier studies have reported on increases in erythemal UV dose up to 10% during the last decades, this study focuses on days with high erythema! UV dose, which is defined as a daily dose at least 15% higher than for 1950s clear-sky conditions (which represent preindustrial conditions with respect to anthropogenic chlorine). Furthermore, the influence of low column ozone, clear-sky/partly cloudy conditions and surface albedo on UV irradiance has been analyzed on annual and seasonal basis. The results of this study show that in the Central Alpine Region the number of days with high UV dose increased strongly in the early 1990s. A large fraction of all days with high UV dose occurring in the period 1974-2003 was found especially during the years 1994-2003, namely 40% at Davos, 54% at Hoher Sonnblick and 65% at Vienna. The importance of total ozone, clear-sky/partly cloudy conditions and surface albedo (e.g. in dependence of snow cover) varies strongly among the seasons. However, overall the interplay of low total ozone and clear-sky/partly cloudy conditions led to the largest fraction of days showing high erythemal UV dose. Furthermore, an analysis of the synoptic weather situation showed that days with high erythemal UV dose, low total ozone and high relative sunshine duration occur at all three stations more frequently during situations with low pressure gradients or southerly advection. (C) 2010 Elsevier B.V. All rights reserved.
37. Global sensitivity analysis for assessing the parameters importance and setting a stopping criterion in a biomedical inverse problem.
- Author
-
Rapadamnaba R, Ribatet M, and Mohammadi B
- Subjects
- Humans, Uncertainty, Hemodynamics
- Abstract
This paper shows how to obtain in addition to the standard deviations available after a data assimilation procedure based on the ensemble Kalman filter, an apportioning of the total uncertainty in the outputs of a patient-specific blood flow model into small portions of uncertainty due to input parameters. Statistical indicators generally used for identifying the importance of numerical parameters, namely the Sobol' first order and total indices, are introduced and discussed. These allow the identification of the importance rank of the different input parameters for the patient-specific blood flow model, as well as the influence of the interactions between these parameters on the model output variance. The results show that knowing the importance rank of the model input parameters during the assimilation procedure is useful to avoid unnecessary over-solving and to find a suitable stopping criterion in clinical situations where faster diagnosis is always requested. Indeed, the work permits to reduce typically by a factor of six the time to solution and most importantly with very limited extra calculation using already available information., (© 2021 John Wiley & Sons Ltd.)
- Published
- 2021
- Full Text
- View/download PDF
38. ABC random forests for Bayesian parameter inference.
- Author
-
Raynal L, Marin JM, Pudlo P, Ribatet M, Robert CP, and Estoup A
- Subjects
- Biometry, Computer Simulation, Genetics, Population, Humans, Likelihood Functions, Bayes Theorem
- Abstract
Motivation: Approximate Bayesian computation (ABC) has grown into a standard methodology that manages Bayesian inference for models associated with intractable likelihood functions. Most ABC implementations require the preliminary selection of a vector of informative statistics summarizing raw data. Furthermore, in almost all existing implementations, the tolerance level that separates acceptance from rejection of simulated parameter values needs to be calibrated., Results: We propose to conduct likelihood-free Bayesian inferences about parameters with no prior selection of the relevant components of the summary statistics and bypassing the derivation of the associated tolerance level. The approach relies on the random forest (RF) methodology of Breiman (2001) applied in a (non-parametric) regression setting. We advocate the derivation of a new RF for each component of the parameter vector of interest. When compared with earlier ABC solutions, this method offers significant gains in terms of robustness to the choice of the summary statistics, does not depend on any type of tolerance level, and is a good trade-off in term of quality of point estimator precision and credible interval estimations for a given computing time. We illustrate the performance of our methodological proposal and compare it with earlier ABC methods on a Normal toy example and a population genetics example dealing with human population evolution., Availability and Implementation: All methods designed here have been incorporated in the R package abcrf (version 1.7.1) available on CRAN., Supplementary Information: Supplementary data are available at Bioinformatics online., (© The Author(s) 2018. Published by Oxford University Press. All rights reserved. For permissions, please e-mail: journals.permissions@oup.com.)
- Published
- 2019
- Full Text
- View/download PDF
Catalog
Discovery Service for Jio Institute Digital Library
For full access to our library's resources, please sign in.