Performance comparison of MSER-5 and N-Skart on the simulation start-up problem

Authors:
Anup C. Mokashi;Jeremy J. Tejada;Saeideh Yousefi;Ali Tafazzoli;Tianxiang Xu;James R. Wilson;Natalie M. Steiger
Affiliations:
North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC;Metron Aviation, Inc., Dulles, VA;North Carolina State University, Raleigh, NC;North Carolina State University, Raleigh, NC;University of Maine, Orono, ME
Venue:
Proceedings of the Winter Simulation Conference
Year:
2010

Citing 4
Cited 2

A comparison of five steady-state truncation heuristics for simulation

Proceedings of the 32nd conference on Winter simulation
Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)

Simulation Modeling and Analysis (McGraw-Hill Series in Industrial Engineering and Management)
Stationarity tests and MSER-5: exploring the intuition behind mean-squared-error-reduction in detecting and correcting initialization bias

Proceedings of the 40th Conference on Winter Simulation
N-Skart: a nonsequential skewness- and autoregression-adjusted batch-means procedure for simulation analysis

Winter Simulation Conference

Interval estimation using replication/deletion and MSER truncation

Proceedings of the Winter Simulation Conference
Factors affecting warm-up periods in discrete event simulation

Simulation

Quantified Score

Hi-index	0.00

Visualization

Abstract

We summarize some results from an extensive performance comparison of the procedures MSER-5 and N-Skart for handling the simulation start-up problem. We assume a fixed-length simulation-generated time series from which point and confidence-interval (CI) estimators of the steady-state mean are sought. MSER-5 uses the data-truncation point that minimizes the half-length of the usual batch-means CI computed from the truncated data set. N-Skart uses a randomness test to determine the data-truncation point beyond which spaced batch means are approximately independent of each other and the simulation's initial condition; then using truncated nonspaced batch means, N-Skart exploits separate adjustments to the CI half-length that account for the effects on the distribution of the underlying Student's t-statistic arising from skewness and autocorrelation of the batch means. In most of the test problems, N-Skart's point estimator had smaller bias than that of MSER-5; moreover in all cases, N-Skart's CI estimator outperformed that of MSER-5.