Level of Education
5 years of post-secondary education
ECTS
2 credits
Training Structure
College of Sciences
Description
A design of experimentsis the ordered sequence of trials in an experiment whose purpose is to test the validity of a hypothesis by reproducing a phenomenon and varying one or more parameters. Each trial yields data, and all the data generated during an experiment must be analyzed using rigorous methods to determine whether or not the hypothesis is valid. This experimental approach allows us to gain new knowledge by validating a model in a cost-effective manner (using the fewest possible trials, for example).
Starting with a simple problem, this module develops the methodological and statistical tools needed to validate increasingly complex hypotheses in the most optimal way possible. These methodologies are implemented using the R statistical language.
Hourly volumes*:
CM: 3:00 p.m.
Practical work: 5 hours
Objectives
To provide students with the skills necessary to understand the key concepts of experimental designs and to use inferential statistical tools for the design and analysis of experimental designs.
By the end of this module, students should be able to select an experimental design appropriate for their problem and analyze the results in a comprehensive, rigorous, and intellectually sound manner.
Class Hours
- Experimental Design - CMLecture3:00 p.m.
- Experimental Design - LabLab Work5 hours
Mandatory Prerequisites
HAC712X: Chemometrics, Statistical Data Analysis, Design of Experiments
Knowledge Assessment
CC-I
Course Outline
Introduction to the topic of experimental designs: the Hotelling’s weights problem. Review of the concepts of response surface, experimental error, modeling, confidence interval, and hypothesis testing
Comprehensive experimental designs: overview.2p factorial designs, where p = 1, 2, … Multi-level factorial designs:K1 * K2 * … * Kp. Concepts of interaction and synergy. Statistical analysis: analysis of variance, testing of assumptions.
Fractional experimental designs: overview, rationale, limitations. 2-factor factorial designsp-k factorial designs, complete and incomplete block designs, Latin squares, Greco-Latin designs, and Youde designs. Statistical analysis: analysis of variance, testing of assumptions.
Response surface: first- and second-degree models. Estimation and inference. Star designs, D-optimality, and D-optimal designs. Mixture designs.
Additional Information
Administrative contact(s):
Master's in Chemistry Office
https://master-chimie.edu.umontpellier.fr/