The team develops new models and statistical methods for data from epidemiological studies and clinical trials, with a strong emphasis on cohort data analysis.
Objectives
The Biostatistics team develops statistical methods for the analysis of data from epidemiological studies or clinical trials. The major area of research focuses on dynamic models, i.e. all the models to take into account the temporal dimension of events and processes. Some works have a strong theoretical dimension but they are all motivated by applications for natural history, risk factors, diagnosis or prognosis of chronic diseases such as Alzheimer’s disease, AIDS, cancer or disease chronic kidney and by the assessment of the impact of these diseases for Public Health. Software that implements these methods are regularly made available to the scientific community via Internet. To support its activities recruitments are planned.
Research area
Multivariate models for time-dependent data
- Joint models for longitudinal markers and multiple events
- Latent process models
- Multi-state models
- Modeling of protracted exposure in case-control studies
- Evaluation of model assumptions and predictive ability
Model-based estimation of Public Health indicators
- Projection of dementia burden and impact of intervention
- Estimation of HIV infection from several sources of data
Downloads
Find here all our files
- FRAILTYPACK: R package for general frailty models
- CPMTL: Programme de calcul de la P_value pour une série de plusieurs codages d’une variable explicative dans un modèle logistique
- CENSAD: Programme pour l’estimation des paramètres de modèles linéaires mixtes pour données longitudinales gaussiennes censurées à gauche
- AEFNC-P: Correction asymptotique exacte de la P-value pour un nombre fini de tests
- ScreenDEM: Feuille de calcul de la probabilité de démence
- PHMPL: Programme de calcul d’une fonction de risque et d’une fonction de survie lisses par une méthode non-paramétrique basée sur la maximisation d’une vraisemblance pénalisée
- ORDINAL: SAS macro for the estimation of mixed models with ordinal data (proportional odds mixed model and cumulated probit mixed model)
- R code for sparse conditional logistic regression
- PSPMCM: Macro SAS pour l’estimation de modèles de survie de mélange avec une fraction non à risque (Mixture Cure Models)
- HETMIXLIN Program for estimating linear mixed models with a mixture of distribution for the random effects.
- NLMULTIMIX: Program for estimating a non linear mixed model for multivariate longitudinal quantitative non Gaussian data.
- MKVPCI : Programme pour l’estimation des modèles de Markov avec intensités de transition constantes par morceaux et covariables.
- NIMROD : Programme d’inférence en modèles mécanistes (ODE) avec effets aléatoires.
- HETMIXSURV : program for the analysis of multivariate curvilinear possibly heterogeneous longitudinal outcomes and a time-to-event using a latent process approach
- LCMM : A R package for the estimation of latent class mixed models, joint latent class models and mixed models for curvilinear outcomes
- SmoothHazard: A R package for the estimation of illness-death models for interval-censored data
- Projection with Semi-Markov Model
Carreer
If you are interested by research in Biostatistics and more generally Statistics applied to health, send a motivated application to sandrine.darmigny@u-bordeaux.fr. Our biostatistics team welcomes interns, PhD students and postdoctoral researchers each year.
Main publications
- Commenges D and Jacqmin-Gadda H. Dynamical Biostatistical Models. 2015. Ed : CRC Press
- Commenges D and Jacqmin-Gadda H. Modèles Biostatistiques pour l’Epidémiologie. 2015. Ed : De Boeck
- Blanche P, Proust-Lima C, Loubère L, Dartigues JF, Jacqmin-Gadda H. Qantifying and comparing dynamic predictive accuracy of joint models for longitudinal marker and time-to-event in presence of censoring and competing risk events, Biometrics 2015, 71,102-113
- Joly P,Touraine C, Georget A, Dartigues JF, Commenges D, Jacqmin-Gadda H. Prevalence projections of chronic diseases and impact of public health intervention, Biometrics, 2013;69: 109–117.
- Rondeau, V., Mazroui, Y., & Gonzalez, J. R. (2012). frailtypack: an R package for the analysis of correlated survival data with frailty models using penalized likelihood estimation or parametrical estimation. Journal of Statistical Software, 47(4), 1-28.
Details
Centre de recherche INSERM U1219
Université de Bordeaux – ISPED
146 rue Léo-Saignat
33076 BORDEAUX cedex
Tél : +33 (0)5 57 57 13 93
Tél : +33 (0)5 57 57 95 68
Fax : +33 (0)5 56 24 00 81
Informations
Warning: array_merge(): Argument #2 is not an array in /home/insermu897/public_html/wp-content/themes/bphcenter/single.php on line 307
Members
- Ahmadou Alioum
- Marta Avalos
- Sebastien Branchoux
- Daniel Commenges
- Sandrine Darmigny
- Florian Guillet
- Pierre Joly
- Agnieszka Krol
- Karen Leffondre
- Emilie Leveque
- Viviane Philipps
- Cécile Proust-Lima
- Virginie Rondeau
- Anaïs Rouanet
- Denis Rustand
- Camille Sabathé
- Corentin Segalas
- Casimir Ledoux Sofeu
- Bachirou Taddé
- Maude Wagner
