Læringsutbytte

A candidate who has completed the course will have a learning outcome in the form of aquired knowledge, skills, and general competence, as described below.

Knowledge:

The candidate will understand:

• multivariate data analysis techniques and algorithms
• experimental design approaches
• calibration techniques and algorithms
• ability to perform multivariate analyses
• ability to interpret and present results

Skills:

The candidate will be able to:

• program software needed for multivariate analysis (PCA)
• program software for multivariate calibration (PCR, PLS)
• analyze multivariate data
• calibrate multivariate prediction models

Innhold

The contents of the course will vary to some degree between years. In general, the course should give an overview of the more important types of parametric and non-parametric statistical analyses in an ecological context.

The course includes topics within (but not restricted to):

• Multivariate calibration – advanced theory
• Model reduction
• Process monitoring (Projection of Latent Structures, 2PLS)
• Multivariate statistics
• Time series analysis

Exercises and individual assignments will be an important part of the course

Arbeids- og læringsformer

Lectures on selected topics, computer exercises and active discussions, individual problem assignments.

Vurderingsformer

Grades (pass/fail) will be given on a home project carried out by each student independently, which will count for 100 % of the grade.

Det tas forbehold om mindre justeringer i planen.