Output Analysis

Output Analysis - Output Analysis Theresa M. Roeder Spring...

Info iconThis preview shows pages 1–8. Sign up to view the full content.

View Full Document Right Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon

Info iconThis preview has intentionally blurred sections. Sign up to view the full version.

View Full DocumentRight Arrow Icon
This is the end of the preview. Sign up to access the rest of the document.

Unformatted text preview: Output Analysis Theresa M. Roeder Spring 2011 Simulation Output Analysis Perspectives and issues Serial correlation Interval estimation Non-parametric methods (Multiple responses) Perspectives Stages of Study 1. Modeling and validation 2. System evaluations (high-level) 3. System design (details) 4. Implementation P r i m a r y O u t p u t Main Questions: Where and when to spend study resources? Animations Have been mostly physical (not logical) Have made simulations more popular + System interactions + Verification and validation + Training and shop floor credibility + Logic development and testing-Take valuable study resources to develop and maintain-Serve no analytical purpose, maybe negative value-Force a particular framework or world-view Validation: Turing Test Hypothesis: A manager familiar with the real system cannot tell the difference between outputs of the simulation and the outputs of the real system Basic Approach: Give the manager both simulation output and output of the real system and see if (s)he can tell the difference Advantages: If manager cannot tell difference, confidence in model established. If can tell difference, can point out why simulation results are different and the model can be changed to better reflect real system. Statistics We want: Good estimator High accuracy (low bias) Good precision (low variance) General validity (robustness) Meaningful insights (interpretations) Statistics Measurement of Estimator Goodness Sources and effect of bias Interval estimates confidence intervals prediction intervals tolerance intervals etc. etc. etc....
View Full Document

This note was uploaded on 01/26/2012 for the course DS 408 taught by Professor Theresam.roeder during the Spring '12 term at S.F. State.

Page1 / 27

Output Analysis - Output Analysis Theresa M. Roeder Spring...

This preview shows document pages 1 - 8. Sign up to view the full document.

View Full Document Right Arrow Icon
Ask a homework question - tutors are online