Course info

Most quantitative research projects involve both case-specific programming tasks as well as data analysis of a more standard nature. When working with quantitative data it is moreover essential to be able to do so in a systematic and reproducible manner with trustworthy software. This course aims at introducing the free program R as a computational environment for integrating these tasks. R has for two decades been a leading tool for computing with data and it is the preferred language for implementation of new statistical methodology.

The course will cover the practice of scientific computing, programming, and quantitative analyses as well as the essential theoretical underpinnings.

The topics of the course will include.

• Introducing R as a statistical programming environment for data analysis.
• Efficient data management using R.
• High-level graphics in R.
• Statistical models in R
• Aspects of scientific computing in theory and practice.
• Reproducible research in practice
• Programming in R and vectorized computations.
• Optional (if time permits) Matrix factorizations and other numerical methods in R. Easy integration of C++ code in R.

Prerequisites:
Participants must have a working knowledge of elementary statistical methods such as regression models and analysis of variance.

Learning objectives:
After completing the course the participants will
1. be able to solve programming tasks with R.
2. know how to manage data, visualize data and fit models to data using R.
3. have learned enough about R to continue learning on their own.

Teaching methods:
A combination of instructive videos, computer practicals and lectures.

Criteria for assessment:
Active participation in the practicals + approval of major exercise (to be handed in after the course).

Frequently asked questions: