A5024393119- Statistical Methods and Inference
- Bayesian Methods and Mixture Models
- Gaussian Processes and Bayesian Inference
- Control Systems and Identification
- Neural Networks and Applications
- Statistical Methods and Bayesian Inference
- Musculoskeletal pain and rehabilitation
- Statistical Distribution Estimation and Applications
- Advanced Statistical Methods and Models
- Spine and Intervertebral Disc Pathology
- Financial Risk and Volatility Modeling
- Distributed Sensor Networks and Detection Algorithms
- Pain Management and Treatment
- Simulation Techniques and Applications
- Markov Chains and Monte Carlo Methods
- Anesthesia and Pain Management
- Genomic variations and chromosomal abnormalities
- Stochastic Gradient Optimization Techniques
- Probabilistic and Robust Engineering Design
- Soil Geostatistics and Mapping
- Fuzzy Systems and Optimization
- Fractional Differential Equations Solutions
- Statistical and numerical algorithms
- Survey Sampling and Estimation Techniques
- Advanced Multi-Objective Optimization Algorithms
Laboratoire de Mathématiques et Applications
2013-2024
Université de Poitiers
2015-2024
Laboratoire de Mathématiques
2014-2024
Centre National de la Recherche Scientifique
2010-2024
Laboratoire de Mathématiques et de leurs Applications
2013-2023
Institut Pprime
2019-2022
Laboratoire Mathématiques, Image et Applications
2020-2022
Université Paris Cité
2010
Délégation Paris 5
2010
Laboratoire de Mathématiques de Versailles
2006-2008
Abstract Aims Several reports have suggested a relationship between male sex and albuminuria in Type 2 diabetes, but impact on renal function decline has not been established. Our aim was to describe the influence of diabetes. Methods SURDIAGENE, an inception cohort, consisted 1470 people with Patients without replacement therapy ≥ 3 serum creatinine determinations during follow‐up prior end‐stage disease were included study. Estimated glomerular filtration rate calculated using Chronic...
We propose an automatic selection of the bandwidth recursive kernel estimators a probability density function defined by stochastic approximation algorithm introduced Mokkadem et al. (2009a). showed that, using selected and stepsize which minimize MISE (mean integrated squared error) class in (2009a), estimator will be better than nonrecursive one for small sample setting terms estimation error computational costs. corroborated these theoretical results through simulation study.
The pattern of renal function decline prior to cardiovascular (CV) events in type 2 diabetes is not well known. Our aim was describe the association between trajectories and occurrence a CV event.We considered patients with from SURDIAGENE (Survie, Diabete de et Genetique) study (discovery cohort) DIABHYCAR (Non-Insulin-Dependent Diabetes, Hypertension, Microalbuminuria or Proteinuria, Cardiovascular Events, Ramipril) (replication cohort). Global patterns estimated glomerular filtration rate...
The multidimensionality of chronic pain forces us to look beyond isolated assessment such as intensity, which does not consider multiple key parameters, particularly in post-operative Persistent Spinal Pain Syndrome (PSPS-T2) patients. Our ambition was produce a novel Multi-dimensional Clinical Response Index (MCRI), including only intensity but also functional capacity, anxiety-depression, quality life and quantitative mapping, the objective being achieve instantaneous using machine...
In this paper we propose an automatic selection of the bandwidth semi-recursive kernel estimators a regression function defined by stochastic approximation algorithm.We showed that, using selected and some special stepsizes, proposed will be very competitive to nonrecursive one in terms estimation error but much better computational costs.We corroborated these theoretical results through simulation study real dataset.
Persistent Spinal Pain Syndrome Type 2 (PSPS-T2), (Failed Back Surgery Syndrome), dramatically impacts on patient quality of life, as evidenced by Health-Related Quality Life (HRQoL) assessment tools. However, the importance functioning, pain perception and psychological status in HRQoL can substantially vary between subjects. Our goal was to extract profiles based dimensions a sample PSPS-T2 patients identify factors associated with these profiles. Two classes were clearly identified using...
Multiple factors are involved in the variability of host's response to P. falciparum infection, like intensity and seasonality malaria transmission, virulence parasite host characteristics age or genetic make-up. Although admitted nowadays, involvement remains unclear. Discordant results exist, even concerning best-known resistance genes that determine structure function red blood cells. Here we report on a genome-wide linkage association study for infection mild attack among Senegalese...
We propose a recursive distribution estimator using Robbins-Monro's algorithm and Bernstein polynomials. study the properties of estimator, as competitor Vitale's estimator. show that, with optimal parameters, our proposal dominates in terms mean integrated squared error. Finally, we confirm theoretical result throught simulation study.
In this paper, we propose an automatic selection of the bandwidth recursive kernel estimators a regression function defined by stochastic approximation algorithm. We showed that, using selected and stepsize which minimize mean weighted integrated squared error , estimator will be better than non‐recursive one for small sample setting in terms estimation computational costs. corroborated these theoretical results through simulation study real dataset.
In this paper, we consider the alleviation of boundary problem when probability density function has bounded support. We apply Robbins-Monro's algorithm and Bernstein polynomials to construct a recursive estimator. study asymptotic properties proposed then compared our estimator with many others estimators. Finally, confirm theoretical result through simulation using two real datasets.
Persistent pain after spinal surgery can be successfully addressed by cord stimulation (SCS). International guidelines strongly recommend that a lead trial performed before any permanent implantation. Recent clinical data highlight some major limitations of this approach. First, it appears patient outco mes, with or without trial, are similar. In contrast, during trialing, infection rate drops drastically within time and compromise the therapy. Using composite assessment experience previous...
The multidimensionality of chronic pain forces us to look beyond isolated assessment such as intensity, which does not consider multiple key parameters, particularly in patients suffering from post-operative Persistent Spinal Pain Syndrome (PSPS-T2). Our ambition was provide a novel Multi-dimensional Clinical Response Index (MCRI), including only intensity but also functional capacity, anxiety-depression, quality life and objective quantitative mapping assessments, the being capture patient...
Persistent Spinal Pain Syndrome Type 2 (PSPS-T2), (Failed Back Surgery Syndrome), dramatically impacts on patient quality of life, as evidenced by Health-Related Quality Life (HRQoL) assessment tools. However, the importance functioning, pain perception and psychological status in HRQoL can substantially vary between subjects. Our goal was to extract profiles based dimensions a sample PSPS-T2 patients identify factors associated with these profiles. Two classes were clearly identified using...
In a pioneer work, Révész (1973) introduces the stochastic approximation method to build up recursive kernel estimator of regression function $x\mapsto E(Y|X=x)$. However, according (1977), his has two main drawbacks: on one hand, its convergence rate is smaller than that nonrecursive Nadaraya-Watson's estimator, and, other required assumptions density random variable $X$ are stronger those usually needed in framework estimation. We first come back study Révész's estimator. An approach...
In this paper we define and study a new estimator of the regression function when response random variable is subject to right-censoring. The constructed by minimizing mean squared relative error operator where outlier data are present model positive. Under classical conditions establish uniform consistency with rate over compact set asymptotic normality suitably normalized. variance explicitly given.
In this paper, we propose two kernel density estimators based on a bias reduction technique. We study the properties of these and compare them with Parzen–Rosenblatt's estimator Mokkadem, A., Pelletier, M., Slaoui, Y. (2009, 'The stochastic approximation method for estimation multivariate probability density', J. Statist. Plann. Inference, 139, 2459–2478) is estimators. It turns out that, an adequate choice parameters proposed estimators, rate convergence will be faster than classical...
In this paper, we consider the alleviation of boundary problem when probability density function has bounded support.We apply Robbins-Monro's algorithm and Bernstein polynomials to construct a recursive estimator.We study asymptotic properties proposed then compare our estimator with many others estimators.Finally, confirm theoretical result through simulation using two real datasets.
This study delves into the conditional mode estimation of a randomly censored scalar response variable operating within framework strong mixing conditions. We introduce kernel-based estimator for function. The principal contribution this investigation lies in derivation asymptotic distribution and rate convergence newly proposed estimators. These findings are established under set fairly comprehensive structural assumptions governing underlying models. Additionally, we conduct series...
A common allele (402H) of the complement factor H (FH) gene is major risk for age-related macular degeneration (AMD), leading cause blindness in elderly population. Development and progression AMD involves vascular inflammatory components partly by deregulation alternative pathway system (AP). The loss central vision results from atrophy and/or abnormal neovascularization arising choroid. functional link between FH, main inhibitor AP, choroidal (CNV) remains unclear. In a murine model CNV...