42: Output Analysis

"The record of a month’s roulette playing at Monte Carlo can afford us material for discussing the foundations of knowledge" - Karl Pearson.

"Do not put faith in what statistics say until you have carefully considered what they do not say." - William Watt.

Lecture outline: How should the output of simulation runs be analyzed?

1) Output models and analysis.

2) Analysis for terminating simulations.

Method of independent replications.

3) Analysis for steady-state simulations.

Replication/ deletion methods.

Batch means.

Primary reference for this lecture:

“Simulation Modeling and Analysis with Arena” by Tayfur Altiok et al.; Chapter 2, “Discrete-Event Simulation”.

Secondary references for this lecture:

1. “Discrete-event simulation – a first course”, by Leemis and Park; Chapter 2: “Random Number Generation”.

2. "Handbook of Simulation", edited by J Banks, Chapter on Output Analysis by [link]