Experimental Design and Analysis of Multivariate Data

Teaching semester

Autumn

Objectives and Content

The course gives an introduction to important multivariate methods used on spectroscopic, chromatographic and other types of multivariate data from pharmacy, medical diagnosis and plant medicine, aquaculture and petroleum. Important topics are experimental design to achieve maximum information from few experiments, patternrecognition to be able to study complex chemical and biological systems, regression to be able to predict quality from raw materials and processvariables and calibration to achieve fast and precise automated analysis based on modern chemical instrumentation. Software with graphical interface is used for analysis and visualisation of multivariate data.

Learning Outcomes

After completing the course KJEM225 the student will be able to:

• set up and analyse the results from an experimental design.
• explain the assumptions and basic equations in multiple linear regression, and to perform a regression analysis.
• explain and to use methods for response optimisation.
• use latent variables to interpret, classify and predict, and to state the theory behind this.
• do an independent data analysis using chemometric software.

Required Previous Knowledge

Basic principles of mathematics.

Credit Reduction due to Course Overlap

K225: 10 stp. PTEK226: 10 stp

Compulsory Assignments and Attendance

Dataexercises with journal. Compulsory work are valid for six following semesteres.
Compulsory work must be submitted within the given deadlines for the course. Approval of the compulsory work is necessary to get admittance to the written exam.

Forms of Assessment

Written examination (4h)

Examination Support Material

Non- programmable calculator, according to model listed in faculty regulations

Grading Scale

The grading scale used is A to F. Grade A is the highest passing grade in the grading scale, grade F is a fail.