Target audience:

Staff members who want to use R for statistical analysis

Contents:

Some basic tools for descriptive and parametric statistic are presented and investigated using the freeware R.
The objective is to propose useful methods allowing to analyze data or to develop and calibrate models, as well as to learn how to use R.
The course is organized in three sessions of two hours:

• The first session is about descriptive tools for univariate and bivariate data (such as histogram, kernel density, measures of location/variability, ranking, boxplot, covariance, correlation, simple linear regression, qqplot).
• The second session concerns descriptive analysis for multivariate data and big data: Principal component analysis; Multiple linear regression / Estimation by least-square; Supervised and unsupervised clustering methods; Bootstrap.
• The last session is about parametric statistic: Estimator (definition and property); Punctual estimation (by maximal likelihood and Bayesian approach); Information criteria (AIC, BIC, likelihood ratio...); Precision of the estimations (confidence and credible intervals); Test of hypothesis.

Language:

This course is taught in English.

Duration:

1 day

Date:

Thursday, 9 March 2017, 9:00-12:00 and 13:30-16:00

Venue:

Jülich Supercomputing Centre, Besprechungsraum 2, building 16.3, room 315

Number of participants:

minimum 5, maximum 14

Instructor:

Dr. Antoine Tordeux, JSC

Course materials:

Introduction to descriptive and parametric statistic with R