First steps in data analysis with R

Course objective: Introducing basic statistical methods for assessing and visualizing effects of explanatory variables on responses (linear model, Principal Component Analysis and Design of experiments).

Organization: The course is divided into eight sessions. Each session is made of a lecture and (at least) two practical classes. In those in-class practical classes, students are given the opportunity to tackle problem-solving exercises, with or without the use of R.

The following documents are provided for each session:

• a 1h-video lecture: a R tutorial whose slides, data and R script are provided (only for sessions 1 to 5);
  
• a PDF file containing a self-directed learning exercise;
• two PDF files with in-class exercises.

All in-class activities (practical sessions) here.

Examples of recent examination:

• exam
• exam, data

Examination 2024 - 1st session : exam, data

Assignments: see instructions here.

Session 1

Objective: Introducing the principles of statistical inference and especially hypothesis testing. What does the question “Is there an effect of this on that?” mean in practice?

• Video lecture with slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 2

Objective: Introducing the F-test for the group mean comparison.

• Video lecture with slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 3

Objective: Introducing the t-test for the two-group mean comparison, the power of a t-test, the Bonferroni correction for the multiplicity of simultaneous tests.

• Video lecture with slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 4

Objective: Introducing the paired t-test for the two-group mean comparison and the simple linear regression model.

• Video lecture with slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 5

Objective: Introducing the F-test in the simple linear regression model and the prediction issue. The lecture ends with the implementation of an F-test to conclude about group differences between linear effects (an example of interaction effect).

• Video lecture with slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 6

Objective: Choosing the explanatory variables to be included in a linear model, when the issue focuses on a particular effect of interest (with possibly confusing or interaction effects) or, on the contrary, when all explanatory variables are equivalently candidate to enter the model (model selection, information criterion).

• slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 7

Objective: describing multivariate profiles by a limited number of latent scores (Principal Component Analysis).

• slides, data and R script;
  
• Self-directed learning exercise, data and R script;

Session 8

Objective: introducing the basic principles of experimental designs (fractional factorial designs).

• slides and R script;
  
• Self-directed learning exercise;