390047 DK PhD-M: Multi Criteria Decision Analysis with Partial Information (2015S)
Continuous assessment of course work
Labels
Registration/Deregistration
Note: The time of your registration within the registration period has no effect on the allocation of places (no first come, first served).
- Registration is open from Mo 18.05.2015 10:00 to Tu 02.06.2015 00:01
- Deregistration possible until Su 07.06.2015 23:59
Details
max. 15 participants
Language: English
Lecturers
Classes (iCal) - next class is marked with N
- Tuesday 02.06. 09:45 - 13:00 Seminarraum 15 Oskar-Morgenstern-Platz 1 3.Stock
- Tuesday 02.06. 13:15 - 16:30 Seminarraum 15 Oskar-Morgenstern-Platz 1 3.Stock
- Wednesday 03.06. 09:45 - 13:00 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Wednesday 03.06. 13:15 - 16:30 Seminarraum 1 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Monday 08.06. 09:45 - 13:05 Studierzone
- Monday 08.06. 13:15 - 14:45 Studierzone
- Monday 08.06. 15:00 - 16:30 Hörsaal 5 Oskar-Morgenstern-Platz 1 Erdgeschoß
- Tuesday 09.06. 09:45 - 13:00 Seminarraum 5 Oskar-Morgenstern-Platz 1 1.Stock
- Tuesday 09.06. 13:15 - 16:30 Seminarraum 6 Oskar-Morgenstern-Platz 1 1.Stock
Information
Aims, contents and method of the course
Assessment and permitted materials
Assessment method
Class interaction (40%)
Essay about a research paper (60%), to be delivered until July 15(?)Teaching materials
Scientific literature (journal papers)
Class interaction (40%)
Essay about a research paper (60%), to be delivered until July 15(?)Teaching materials
Scientific literature (journal papers)
Minimum requirements and assessment criteria
Syllabus
MCDA overview
The MCDA approach
MCDA decision processes
Panorama of MCDA methods
Additive model with partial information
The additive model
Motivation for the use of partial information
Decision rules
Robustness analysis
Ordinal regression
Stochastic analysis
Extension to group decision
ELECTRE TRI with partial information
The ELECTRE approach
ELECTRE TRI
Robustness analysis
Ordinal regression
Stochastic analysis
Extension to group decision
MCDA overview
The MCDA approach
MCDA decision processes
Panorama of MCDA methods
Additive model with partial information
The additive model
Motivation for the use of partial information
Decision rules
Robustness analysis
Ordinal regression
Stochastic analysis
Extension to group decision
ELECTRE TRI with partial information
The ELECTRE approach
ELECTRE TRI
Robustness analysis
Ordinal regression
Stochastic analysis
Extension to group decision
Examination topics
Teaching methods
Presentation of the themes promoting debate (student-student and student-teacher).
Solving of cases that illustrate the practical relevance of the themes and different decision aiding strategies.
Role-playing.
Discussion of application examples from the literature
Presentation of the themes promoting debate (student-student and student-teacher).
Solving of cases that illustrate the practical relevance of the themes and different decision aiding strategies.
Role-playing.
Discussion of application examples from the literature
Reading list
Association in the course directory
Last modified: Mo 07.09.2020 15:46
Multi-Criteria Decision Analysis (MCDA) consists of formal approaches which consider explicitly multiple criteria in helping individuals or groups explore decisions that matter to them. MCDA suggests a structured way to conduct a process, encompassing the activities of structuring the problem situation, building an evaluation, and applying this model to derive recommendations. In MCDA, translating the preferences and values of the individuals or groups into a formal mathematical model is often difficult. Requiring partial information can then be useful to advance in the decision process in a way that is more comfortable for the actors involved in the analysis. This course focuses on how MCDA can be conducted using partial information, reviewing recent research in this very active area. Two distinct MCDA methods will be addressed in detail, in order to present different methodological approaches that can be extended to other MCDA methods.Learning outcomes upon completing this course
The student will know the different stages of a decision process and the information to be gathered and organized, recognizing the advantages that an MCDA modelling framework may present.
The student will be capable of applying the additive value function model and the ELECTRE TRI model, understanding the role of the parameters to be elicited.
The student will be able to anticipate difficulties that can potentially hinder the elicitation of information from the actors involved in MCDA.
The student will identify different types of partial information and how such information can be translated to an MCDA model in the form of mathematical constraints.
Given partial information, the student will be able to apply simple decision rules, to obtain robust conclusions using mathematical programming techniques, and to obtain statistics using simulation.
The student will have a holistic vision about the tools to deal with partial information and how they may be useful in the context of a decision process, from the perspective of an analyst.
The student will be aware of and will be able to put into context recent research in this area, potentially building on this research for his or her own research work.
In addition, these learning outcomes contribute to develop several generic skills, namely those of critical reasoning, analysis and synthesis, problem solving, information interpretation and management, and group interaction.