Problems in the Statistical Analysis of Simulation Experiments: The Comparison of Means and the Length of Sample Records Research is continued into statistical analysis of simulation experiments containing autocorrelated time series. It is shown how to estimate the lengths of sample records needed to use certain large sample results in measuring stability. Analogies between autocorrelated data and independent observations are described. A way to test the difference of the mean of two experiments is suggested. It is shown how the variance of the sample mean relates to the spectrum of the generating process, and estimation of the quantities of interest is described. The results expand the possibilities of statistical spectral analysis as applied to simulation experiments. CACM February, 1967 Fishman, G. S. CA670205 JB February 28, 1978 3:34 PM 1637 5 1637 1637 5 1637 1637 5 1637