Managers face many decision-making challenges at different levels. These challenges emerge from the increasing complexity of today’s dynamic marketplace which is imputable to a high level of uncertainty in supply and demand, conflicting objectives, the vagueness of information, and numerous decision variables and constraints. Robust tools are needed to support these decisions and to enable managers to evaluate the impact of decisions before their actual implementation.
This module provides an introduction to simulation and how it applies to the study and analysis of business processes for decision support. The module provides an in-depth working knowledge of the application of discrete-event simulation concepts and tools to improve or design a system in industry and business. It also encompasses a number of statistical techniques that have been developed within the field of quantitative management to support the decision-making process.
Introduction to simulation; Random number generation; Discrete and continuous random variables; Summary measures of random variables; Law of large numbers; Central limit theorem; Confidence intervals; simulations for the single-server queue, and simple project management; Understanding the power and the limitations of simulation.
Understand how uniform random numbers are generated; Understand what is a Poisson process; Generate a Poisson process; Generate Normal random variables; how to use historical data to decide on simulation input; Make histogram, bar, and Q-Q plots to help decide on the appropriate input distribution; Estimate the input distribution parameters; Perform chi-square and Kolmogorov-Smirnov goodness-of-fit tests.
Become familiar with the simulation software environment; understand the difference between terminating and steady-state simulations; Understand the challenges of steady-state simulation; Define a time average and an ensemble average; build a variety of simulation models; Verification and validation of simulation models.
Simulation output Analysis
Deciding on transient period, run length, and number of replications; Sensitivity Analysis; Design of experiment;
Purpose and concepts of system dynamics; Problem definition and model purpose; building theory with causal loop diagrams; Mapping the stock and flow structure of systems; Dynamics of stocks and flows; linking feedback with stock and flow structure; Analysing Systems and Creating Robust Policies
The module will incorporate a range of learning teaching methods including lectures, tutorials, class assignments, class discussions, software, case studies (best practices), and group projects. The teaching methodology will apply a 30% teacher-centered to 70% student-centered learning approach which will assign significant responsibility to the student in the learning process, for example; in the modeling phase, the participant will analyse the business process and start modeling after learning the basics in the first lectures and from the gained experiences in a different context and practical examples/models. Evaluate the processing logic and taking responsibility for delivering an effective model will be the participant role under the lecture supervision
|Module Content & Assessment