Monday – Classes from 09:30 to 17:30 -

 

 

Reducing dimensionality, the general framework.
An introduction to the notion of multivariate data, to the concept of inertia, to the analysis of multivariate data. From the analysis of the rows to the analysis of the columns: the transition formulae. What is an illustrative variable and how to use it?

Combining the best of two worlds.
Principal Component Analysis, the « usual » way and the « French » way. My first PCA on gene expression data, with R: practical overview of multivariate packages.

 

 

 

 

Tuesday – Classes from 09:30 to 17:30

 

Visualisation issues. 
Visualising multivariate data with PCA and R: practical overview of multivariate packages.

Analysing a contingency table.
From PCA to Correspondence Analysis: taking into account the intrinsic nature of the data. A brief reminder of the notion of Khi-square test. Analysing the matrix of deviance: when bivariate means multidimensional. CA applied to RNA-Seq data.

 

 

 

Wednesday – Classes from 09:30 to 17:30

 

 

When individuals are described by categorical variables.
From CA to Multiple Correspondence Analysis: analysing a complete disjunctive data set. The specificities of MCA.
Mapping genes according to the biological functions they are involved in.

Unsupervised clustering based on principal components. Getting an automatic description of the clusters.

 

 

 

 

Thursday – Classes from 09:30 to 17:30

 

Integrating heterogenous datasets in a multidimensional analysis.
Defining the notion of multiple dataset. Comparing Generalised Canonical Analysis and Multiple Factor Analysis, from a genomic perspective. An introduction to Multiple Factor Analysis: analysing groups of variables that describe the same set of individuals.

Application to the comparison of different ways of coding a same information, comparing the structure induced by different data sets.

 

 

 

 

Friday – Classes from 09:30 to 17:30

 

Combining continuous and categorical variables within a same multidimensional analysis.
Taking into account missing data with principal component based strategies.
Any questions?