The Research Group on Compositional Data Analysis of the University of Girona (UdG) organise and deliver compositional data analysis courses in person and online. A one week long course (the week-CoDaCourse) is held in person in July every year. An online version (the online CoDaCourse) is permanently open for registration. Special one-day courses are also delivered on demand.

The courses are taught in English language.

These courses introduce the methodological and practical aspects of the statistical analysis of compositional data, as well as serving as an informal discussion forum on more advanced modelling topics.

They present the current state of the art in the field and cover the following topics:

  • Hypothesis underlying statistical data analysis (sample space, scale).
  • The Aitchison geometry of the simplex.
  • Coordinate representation; distributions on the simplex.
  • Exploratory analysis (centering, variation array, biplot, balances-dendrogram).
  • Pre-processing irregular data: outliers, missing data and zeros.
  • Multivariate analysis with CoDa: regression, cluster, MANOVA, and discriminant analysis.
  • Introduction to available software: CoDaPack and R-packages.

Bring your own data sets

...ask, discuss, work, make progress!

The CoDaCourses consist of a flexible mixture of lectures and practical sessions. The practicals are carried out using the freeware stand-alone CoDaPack and the package and other specialised packages like zCompositions on the R open-source statistical computing system. A number of realistic datasets are used as basis to guide the participants through the learning process and discuss particular issues interactively.

Statisticians and applied scientists dealing with compositional data in any field of knowledge, either from academia or industry, are strongly encouraged to take our courses. As background, it is recommended to have taken a one semester undergraduate course in statistics and mathematics. Basic knowledge of multivariate data analysis will also come in handy.

The CoDaCourses are organized by the members of the Research Group on Compositional Data Analysis at the Dept. Informàtica, Matemàtica Aplicada i Estadística (IMAE-UdG) under the projects METhods for COmpositional analysis of DAta (CODAMET) and COmpositional and Spatial Data Analysis (COSDA). The core team of instructors includes also members from the Technical University of Catalonia (UPC), and the University of Lleida (UdL).

The courses are accredited by the International Association for Mathematical Geosciences (IAMG) since 2011 and by the CoDa-Association since 2017. Several editions were supported by the Statistical Modelling Society (SMS) and promoted by the ERS-IASC. Discounted fees are available for students and members of the CoDa-Association and Spanish Society of Statistics and Operations Research (SEIO)

The online CoDaCourse

Registration is open!

This is the online version of the CoDaCourse and covers the same topics. The development, materials and evaluation of the course are tailored to the distance learner. Those enrolled in this course can set their own pace according to availability. They will be assigned a personal tutor who will discuss and assess progress with the student throughout the course.

Acredited by:

Supported by:

The 11th week-CoDaCourse

Note that, as we will be busy holding CoDaWork'24 conference (3-7 June 2024), the next one-week CoDaCourse in person has been rescheduled to be held in July 2025. Sorry for any inconvenience this might cause. As an alternative, you might be interested in joining the pre-conference one-day Introduction to Compositional Data Analysis to be held in person on the 3th of June 2024. You can find further details and register at CoDaWork'24

This course provides an introduction to the methodological and practical aspects of the statistical analysis of compositional data, as well as an informal forum for discussion. The lectures review the fundamentals and the current state of the art in the field. The practical sessions focus on the application of CoDa techniques and their interpretation using current software packages, the stand-alone point-and-click CoDaPack and specialised packages on the R system for statistical computing. An open discussion session is also planned. The attendants are encouraged to bring their own research problems and data sets for discussion.

Recommended background: One semester undergraduate courses in statistics and mathematics. Familiarity with multivariate data analysis will be beneficial.

Acredited by:

Supported by:

List of CoDaCourses

simply select the one that best suits your needs