On strong consistency of the variance estimator

ABSTRACT

One way to construct a confidence interval for the mean constant of a stochastic process, is via consistent estimation of another parameter of the process, namely, the time-average variance constant. In this paper, we discuss strong consistency of the variance estimator for several methods of steady-state output analysis. These are; Batch Means (BM), Overlapping Batch Means (OBM), Spectral methods, and finally, Standardized Time Series (the area estimator of STS). A characterization of the spectral variance estimator is also presented; it is a generalization of OBM. Another estimator, which might be called Overlapping Area estimator, connects the area estimator with spectral methods.

REFERENCES

• 1: Chow, Y.S., and Robbins, H. (1965). On the asymptotic theory of fixed-width sequential confidence intervals for the mean. Annals of Mathemalical Stastics, 36. 457-462.
• 2: Damerdji, H. (1987). Strong consistency of the variance estimator in steady-state output analysis. In preparation
• 3: Peter W. Glynn , Donald L. Iglehart, Large-sample theory for standardized time series: an overview, Proceedings of the 17th conference on Winter simulation, p.129-134, December 11-13, 1985, San Francisco, California, United States [doi>10.1145/21850.253097]
• 4: Glynn, P.W., and Iglehart, D.L., (1988). The theory of standardized time series. To appear in Mathematics of Operations Research.
• 5: philip, W., and Stout, W., (1975). ALmost sure invariance principles for partial sums of weakly dependent random variables. Memoir of the American Mathematical Society, 164.
• 6: Meketon, M.S., (1980). The varianee time-curve: theory, estimation, and application. Ph.D. Dissertation, School of Operations Research and Industrial Engineering, Cornell University, Ithaca, New York.
• 7: Marc S. Meketon , Bruce Schmeiser, Overlapping batch means: something for nothing?, Proceedings of the 16th conference on Winter simulation, p.226-230, December 28-30, 1984, Dallas, TX
• 8: Priestley, M.B., (1981). Spectral Analysis and Time Series. Academic Press, London.
• 9: Schruben, L.W., (1983). Confidence interval estimation using standardized time series. Operations Research, 31, 1090- 1108.

INDEX TERMS

Primary Classification:
  G. Mathematics of Computing

Additional Classification:
  I. Computing Methodologies
  I.6 SIMULATION AND MODELING

General Terms:
Design, Performance, Theory