Teaching Activities
Modelling [2018-2019] lecture
Paris-Dauphine
Teaching hours: 6
- Handling missing values using multiple imputation
- Multiple imputation methods for large data sets
Material :
Data analysis (STA101)[2018-2020] lecture and tutorial
CNAM, Paris
Teaching hours: 75
- Univariate and bivariate analysis
- Principal components methods (PCA, CA, MCA, FAMD) with or without missing values
- Clustering (k-means, hierarchical methods)
Material
CNAM, Paris
Teaching hours: 75
- Simulation and MCMC methods
- Estimation : maximum likelihood, Fischer information, Cramer Rao bound
- Confidence intervals
- Tests for means, variances, proportions
- Tests for paired samples
- Goodness of fit tests and test of independence
- Non-parametric statistics
Storage and data mining (STA211)[2018-2020] lecture and supervision of students' projects
CNAM, Paris
Teaching hours: 50
- Preprocessing
- Data and strategies for data mining
- Data mining for modern data
Biostatistic [2017-2019] lecture and tutorials (M1)
Cnam-Pasteur, Paris
Teaching hours: 36
- Statistical inference (estimator, bias, variance, convergence, central limit theorem, classical confidence intervals)
- Statistical tests for 2 groups
- Univariate and bivariate analysis
Assessment of analysis methods for biosciences [2016] tutorials (L1)
Université Paris-Diderot, Paris
Teaching hours: 64
- Descriptive statistics
- Elementary probability (independence, condional probabilities, Bayes theorem)
- Random variables (density function, cumulative distribution function, expectation, variance)
- Sum of random variables (convergence in distribution, central limit theorem)
- Statistical tests (Khi-2, Fisher, z-test, Wilcoxon)
Biostatistic and R software [2016-2017] lecture and tutorials (M1)
Université Paris-Diderot, Paris
Teaching hours: 6
- Statistical inference (estimator, bias, variance, convergence, central limit theorem, classical confidence intervals)
- Statistical tests for 3 groups (ANOVA, Kruskal-Wallis, Khi-2, Fisher)
- Statistical tests for categorical variables (Khi-2, Fisher, McNemar)
Modelling [2016-2017] lecture and tutorial (M2)
Université Paris-Diderot, Paris
Teaching hours: 2
- Handling missing values using multiple imputation
General statistics [2012-2015] tutorials and supervision of students' projects (Licence 2/Master 1)
Agrocampus-Ouest, Rennes
Teaching hours: 160
Video lecture
- Multiple linear regression
- Analysis of variance with several factors and interaction
- Fractional factorial design
- Principal Components Analysis (PCA)
Analysis of survey data [2013-2015] tutorials and supervision of students' projects (Licence 3)
Agrocampus-Ouest, Rennes
Teaching hours : 45
Lecture
- Multiple Correspondance Analysis (MCA)
- Hierarchical Clustering on Principal Components (HCPC)
Sensometry [2013] tutorials and supervision of students' projects (Licence 3)
Agrocampus-Ouest, Rennes
Teaching hours : 15
Video lecture
- Characterization of products
- Performance of a panel
- Preference mapping
Paris-Dauphine
Teaching hours: 6
- Handling missing values using multiple imputation
- Multiple imputation methods for large data sets
Material :
Data analysis (STA101)[2018-2020] lecture and tutorial
CNAM, Paris
Teaching hours: 75
- Univariate and bivariate analysis
- Principal components methods (PCA, CA, MCA, FAMD) with or without missing values
- Clustering (k-means, hierarchical methods)
Material
- week 1 : information - lecture - tutorial
- week 2 : lecture - tutorial
- week 3 : lecture - tutorial
- week 4 : lecture - tutorial
- week 5 : lecture - tutorial
- week 6 : lecture - tutorial
CNAM, Paris
Teaching hours: 75
- Simulation and MCMC methods
- Estimation : maximum likelihood, Fischer information, Cramer Rao bound
- Confidence intervals
- Tests for means, variances, proportions
- Tests for paired samples
- Goodness of fit tests and test of independence
- Non-parametric statistics
Storage and data mining (STA211)[2018-2020] lecture and supervision of students' projects
CNAM, Paris
Teaching hours: 50
- Preprocessing
- Data and strategies for data mining
- Data mining for modern data
Biostatistic [2017-2019] lecture and tutorials (M1)
Cnam-Pasteur, Paris
Teaching hours: 36
- Statistical inference (estimator, bias, variance, convergence, central limit theorem, classical confidence intervals)
- Statistical tests for 2 groups
- Univariate and bivariate analysis
Assessment of analysis methods for biosciences [2016] tutorials (L1)
Université Paris-Diderot, Paris
Teaching hours: 64
- Descriptive statistics
- Elementary probability (independence, condional probabilities, Bayes theorem)
- Random variables (density function, cumulative distribution function, expectation, variance)
- Sum of random variables (convergence in distribution, central limit theorem)
- Statistical tests (Khi-2, Fisher, z-test, Wilcoxon)
Biostatistic and R software [2016-2017] lecture and tutorials (M1)
Université Paris-Diderot, Paris
Teaching hours: 6
- Statistical inference (estimator, bias, variance, convergence, central limit theorem, classical confidence intervals)
- Statistical tests for 3 groups (ANOVA, Kruskal-Wallis, Khi-2, Fisher)
- Statistical tests for categorical variables (Khi-2, Fisher, McNemar)
Modelling [2016-2017] lecture and tutorial (M2)
Université Paris-Diderot, Paris
Teaching hours: 2
- Handling missing values using multiple imputation
General statistics [2012-2015] tutorials and supervision of students' projects (Licence 2/Master 1)
Agrocampus-Ouest, Rennes
Teaching hours: 160
Video lecture
- Multiple linear regression
- Analysis of variance with several factors and interaction
- Fractional factorial design
- Principal Components Analysis (PCA)
Analysis of survey data [2013-2015] tutorials and supervision of students' projects (Licence 3)
Agrocampus-Ouest, Rennes
Teaching hours : 45
Lecture
- Multiple Correspondance Analysis (MCA)
- Hierarchical Clustering on Principal Components (HCPC)
Sensometry [2013] tutorials and supervision of students' projects (Licence 3)
Agrocampus-Ouest, Rennes
Teaching hours : 15
Video lecture
- Characterization of products
- Performance of a panel
- Preference mapping
