Multivariate Datanalysis and Chemometrics

Academic Study Board of the Faculty of Engineering

Teaching language: English
EKA: T210032102
Censorship: Second examiner: None
Grading: Pass/Fail
Offered in: Odense
Offered in: Autumn
Level: Master

Course ID: T210032101
ECTS value: 5

Date of Approval: 31-08-2018


Duration: 1 semester

Version: Archive

Course ID

T210032101

Course Title

Multivariate Datanalysis and Chemometrics

ECTS value

5

Internal Course Code

K-MDA

Responsible study board

Academic Study Board of the Faculty of Engineering

Date of Approval

31-08-2018

Course Responsible

Name Email Department
Massimiliano Errico maer@kbm.sdu.dk

Programme Secretary

Name Email Department City
Tina Carøe Sørensen tcs@tek.sdu.dk

Offered in

Odense

Level

Master

Offered in

Autumn

Duration

1 semester

Mandatory prerequisites

Knowledge of elementary statistics is required, e.g. from 4. semester on BSc in Engineering (Chemistry and Biotechnology).

Learning objectives - Knowledge

  • Explain the statistical methods simple and (multivariate) multiple linear regression, principal component analysis, principal component regression and partial least squares, both in scalar and matrix/vector notation.
    • Explain the main challenges and to identify the issues that can appear in chemometric calibration exercises.
    • Explain the selection of the number of scores.

    Learning objectives - Skills

    • Apply the most important chemometric methods to solve selected multivariate calibration problems.
      • Apply a statistical software package, such as R, for solving concrete multivariate calibration problems.
      • Describe and conclude from result of a chemometric analysis and in the form of a report.

      Learning objectives - Competences

      • Describe the advantages and disadvantages of different chemometric methods, in order to choose the correct method to solve a given multivariate calibration problem.
        • Describe the main methods for validation and optimization of a given calibration method for a specific problem, in order to assess the correctness of the method in the given context.

        Content

        • Repetition of basic concepts from statistics and matrix algebra. 
          • Introduction to chemometrics and multivariate calibration.  
          • Multiple linear regression analysis (MLR). 
          • The classical least squares method (CLS). 
          • Principal components analysis (PCA). 
          • Principal components regression (PCR). 
          • Partial least squares regression (PLS). 
          • Validation and optimization of calibration model.

          URL for Skemaplan

          Teaching Method

          Lessons:
          2 hours of lectures and 2 hour problem sessions/exercises per week for 12 weeks. 

          Number of lessons

          48 hours per semester

          Teaching language

          English

          Examination regulations

          Exam regulations

          Name

          Exam regulations

          Tests

          Exam

          EKA

          T210032102

          Name

          Exam

          Description

          Three projects with 3 project reports with analyses of chemometric data sets must be handed in on time and in accordance with the requirements specified at the start of the semester. 

          Assessment by the teacher of the three reports.

          Form of examination

          Internship, written report

          Censorship

          Second examiner: None

          Grading

          Pass/Fail

          Identification

          Student Identification Card - Exam number

          Language

          English

          ECTS value

          5

          Additional information

          The course is held jointly with a course by the same name offered by the Faculty of Science.

          Courses offered

          Offer period Offer type Profile Education Semester

          Studieforløb

          Profile Education Semester Offer period