Christophe Lalanne

September 29th, 2015

This course is a short and practical introduction to statistical analysis of experimental data.

- We will not cover mathematical statistics, but we will focus on
**applied statistics**. - We will not provide a complete account of statistical modeling.
- Examples will come from various disciplines: experimental psychology, medicine, biomedical engineering.
- We will try to emphasize the
**interpretation of results**, and how to get them right.

- Time: 9:00â€“11:00, every Tuesday
- Prerequisites: basic math and experimental design (AMS, previous exposition, or more?)
- Statistical packages: R (sessions 1 to 7), Python (sessions 8 to 11)
- Resources: Handouts available on Github, open access textbook
- Homeworks: short quizzes to complete at home
- Grading: assignements + final project

Christophe Lalanne [R], Sylvain Charron [Py].

- Introduction to R and data analysis (Sep. 29)
- Descriptive statistics, association measures (Oct. 6)
- Inferential statistics and two-group comparisons (Oct. 13)
- Experimental design and ANOVA (Oct. 20)
- Simple and multiple linear regression (Nov. 3)
- The linear model and its applications (Nov. 10)
- Categorical data and two-ways tables (Nov. 17)

Sessions 8 to 11 with Python will consist in replicating analyses done in R.

**OpenIntro Statistics**

http://www.openintro.org/stat/

- 10 to 15 pages to read before each course
- Additional information will be given during the course
- Topics not covered in the textbook will be detailed on the course homepage

**Learning Statistics with R**

http://health.adelaide.edu.au/psychology/ccs/teaching/lsr/

Once more

- 10 to 15 pages to read
- Focus on statistics applied to psy research