A methodological approach to analysis and evaluation of decision systems

The purpose of this research was to develop a basis for a more coherent methodology for the design, implementation, and evaluation of decision systems. The methodology consists of applying Markovian and Bayesian probability techniques to the analysis of evaluated decision maker responses with respec...

Full description

Saved in:
Bibliographic Details
Published inCOMPSAC 79. Proceedings. Computer Software and The IEEE Computer Society's Third International Applications Conference, 1979 pp. 764 - 769
Main Authors Lee, M.J., Ernst, R.L.
Format Conference Proceeding
LanguageEnglish
Published IEEE 1979
Subjects
Bayesian methods
Computer displays
Decision making
Decision support systems
Design methodology
Humans
Information analysis
Information systems
Monte Carlo methods
System performance
Online AccessGet full text
DOI10.1109/CMPSAC.1979.762597

Cover

More Information
Summary:The purpose of this research was to develop a basis for a more coherent methodology for the design, implementation, and evaluation of decision systems. The methodology consists of applying Markovian and Bayesian probability techniques to the analysis of evaluated decision maker responses with respect to display information in sequential decision making. A configuration of display information was analyzed. Utilizing Monte Carlo techniques, a decision situation was simulated with human subjects serving as decision makers. Results of this study indicate that the performance of decision makers is directly associated with the quality of information presented.
DOI:10.1109/CMPSAC.1979.762597