Description:

Modern laboratory equipment produces huge amounts of experimental data — spectral vectors with hundreds of wavelengths, microarrays, gene expression data, sensors, multi-channel images and many others. Even conventional measurements may end up with tens to hundreds of variables. Such data represent a wealth of potential information but usually only a part of it relates to a problem of interest.

This course teaches how to extract problem-dependent information from multivariate data. The practical part of the course assuming using R for calculations and visualization of results.

The course is split in to two parts. The first part (3 days, 2 ECTS) introduces descriptive and inferential statistics, as well as data exploration with Principal Component Analysis. The second part (3 days, 2 ECTS) is mainly devoted to supervised analysis of multivariate data, including regression and validation, preprocessing and variable selection as well as classification.

In each part lectures are supplemented with a suite of real life examples and exercises as well as assignments, with which students will try the discussed methods by solving various data analysis problems. To complete the course, participants have to work on three mini-projects and submit their results in form of reports within 1 month after the main part if finished.

Disclaimer:
DDSA has explicit permission from Arcanic and the owners of the https://phdcourses.dk/ website to display the courses on ddsa.dk.