Discrete data analysis.

Teacher(s)

El Ghouch Anouar;

Language

French

Main themes

- Multinomial Distribution : marginal and conditional distributions and asymptotic properties - Two ways Contingency Tables : Independance and Homogeneity, measures of association and particular tests (Fisher, Mac Nemar, etc.). - Multiple ways Contingency Tables : Mutual, Partial and Conditional Independencies. - Log-linear Models. - Conditional Models - Generalized Linear Models - Logit and Probit Models - Multinomial Discriminant Analysis - Selection of explanatory variables

Aims

At the end of this learning unit, the student is able to :
1	The student will be able to use the basic techniques of Discrete Data Analysis and to apply these to real data using statistical softwares

Content

Content - Multinomial Distribution : marginal and conditional distributions and asymptotic properties - Two ways Contingency Tables : Independance and Homogeneity, measures of association and particular tests (Fisher, Mac Nemar, etc.). - Multiple ways Contingency Tables : Mutual, Partial and Conditional Independencies. - Log-linear Models. - Conditional Models - Generalized Linear Models - Logit and Probit Models - Multinomial Discriminant Analysis - Selection of explanatory variables Methods The course is concentrated on the first ten weeks. The following 4 weeks are devoted to the realization by each student of an empirical study of suitable data.

Evaluation methods

Due to the COVID-19 crisis, the information in this section is particularly likely to change.

Each student is provided a data set to be analyzed by the taught techniques. This analysis is the object of a report orally presented by the student to the Professors. During this presentation, the Professors may question the student on the matter of the course.

Other information

Prerequisites : Elementary courses in Probability and Statistics

Teaching materials

• transparents sur moodle

Faculty or entity

LSBA