Large-sample theory for standardized time series: an overview

ABSTRACT

There are two basic approaches to constructing confidence intervals for steady-state parameters from a single simul t on run. The fir t s to consistently estimate the variance constant in the relevant central limit theorem. This is the approach used in the regenerative, spectral, and autoregressive methods. The second approach (standardized time series, STS) due to SCHRUBEN [10] is to “cancel out” the variance constant. This second approach contains the batch means method as a special case. Our goal in this paper is to discuss the large-simple properties of the confidence intervals generated by the STS method. In particular, the asymptotic (as run size becomes large) expected value and variance of the length of these confidence intervals is studied and shown to be inferior to the behavior manifested by intervals constructed using the first approach.

REFERENCES

• 1: Bi l I inclsl ey, P., Convergence of Probabil ity I~easures, John Wi } ey, New York, 1968.
• 2: 8reimar~, L.., Probability, Addison-Wesley, Readincl, Mass., 1968.
• 3: Glynn, P.W., "Some New Results in Regenerative Process Theory," Technical Report No. 60, Dept. of Operations Research, Stanford University, Stanford, CA, 1982.
• 4: Glynn, P.W., "Limit Theorems for the Method of Replication," Technical Summary Report No. 23, Mathematics Research Center, Madison, WI, 1985.
• 5: Glynn, P.W. and D.L. Iglehart, "The Theory of Standardized Time Series," Technical Report No. 32, Dept. of Operations Research, Stanford University, Stanford, CA, 1985.
• 6: Hall, P. and C.C. Heyde, Martingale Limit Theory and its Applications, Academic Press, New York, 1980.
• 7: Iglehart, D.L., "Simulating Stable Stochastic Systems, V: Comparison of Ratio Estimators," May. lles. Logistics Quart., 22, 1975, 553-565.
• 8: Iglehart, D.L., "The Regenerative Method for Simulation Analysis," in Current Trends in Progr~ming Methodology -- Software ModeI ing, (K.M. Chandy and R.T. Hey, editors), Prentice- Hall, Englewood Cliffs, N.J., 1978.
• 9: Schrut)en, L., "Detecting Initialization Bias in Simulation Output," Opns. lies., 30, 1982, 569-590.
• 10: Schrul)en, L., "Confidence Interval Estimation Using Standardized Time Series," Opns. iles., 31, 1983, 1090-1108.