Overlapping Batch Means: Something more for Nothing?

Output analysis methods that provide reliable point and confidence-interval estimators for system performance characteristics are critical elements of any modern simulation project. Remarkable advances in simulation output analysis have been achieved over the last thirty years, in part owing to the application of data-reuse techniques designed to improve estimator accuracy and efficiency. Many of the key insights regarding data reuse are given in the seminal 1984 Winter Simulation Conference paper by Meketon and Schmeiser that is titled “Overlapping Batch Means: Something for Nothing?” and that introduced the method of overlapping batch means (OBM). We trace the development of OBM from the original work of Meketon and Schmeiser, and we discuss some recent extensions of the method.