Access

You are not currently logged in.

Access your personal account or get JSTOR access through your library or other institution:

login

Log in to your personal account or through your institution.

The Analysis of Simulation-Generated Time Series

George S. Fishman and Philip J. Kiviat
Management Science
Vol. 13, No. 7, Series A, Sciences (Mar., 1967), pp. 525-557
Published by: INFORMS
Stable URL: http://www.jstor.org/stable/2627694
Page Count: 33
  • Download ($30.00)
  • Cite this Item
The Analysis of Simulation-Generated Time Series
Preview not available

Abstract

This study applies spectral analysis to the study of time series data generated by simulated stochastic models. Because these data are autocorrelated, analysis by methods applicable to independent observations is not possible. Mathematical models known as covariance stationary stochastic processes are useful representations of autocorrelated time series. The increased publication of literature describing stochastic processes and spectral analysis, in particular, is making these ideas available to an increasing audience. Section I presents a rationale for our interest in time series models and spectral analysis. Section II describes the basic notions of covariance stationary processes. It emphasizes the equivalence of these processes in both the time and frequency domains; the compactness of frequency domain analysis seemingly recommends it over correlation analysis. Section III provides a heuristic background for understanding statistical spectral analysis. Simple frequency-domain statistical properties are emphasized and compared with the rather involved sampling properties of estimated correlograms. Several relevant statistical tests are described. Three simulated experiments are used as examples of how to apply spectral analysis. These are described in Section IV. They are (1) a single-server, first-come-first-served (FCFS) queueing problem with Poisson arrivals and exponentially distributed service times; (2) a similar model with the FCFS assignment rule replaced by one that chooses the job with the shortest service time; and (3) yet another similar model, but with constant service time. In this third example both assignment rules are equivalent. The state of the queue was observed and recorded at unit intervals for all three examples and forms the time series on which Section V is based; theoretical and statistical correlograms and spectra are compared for example 1; examples 1 and 2 are compared using estimated correlograms and spectra; example 3 serves to show some unusual properties of spectra. A particular conclusion of this paper is that differences in the statistical properties of queue length that result under various assumptions and operating rules are easily identified using spectral analysis. More generally, however, this estimation procedure provides a tool for (1) comparing simulated time series with real-world data, and (2) for understanding the implications that various alternative assumptions have on the output of simulated stochastic models.

Page Thumbnails

  • Thumbnail: Page 
525
    525
  • Thumbnail: Page 
526
    526
  • Thumbnail: Page 
527
    527
  • Thumbnail: Page 
528
    528
  • Thumbnail: Page 
529
    529
  • Thumbnail: Page 
530
    530
  • Thumbnail: Page 
531
    531
  • Thumbnail: Page 
532
    532
  • Thumbnail: Page 
533
    533
  • Thumbnail: Page 
534
    534
  • Thumbnail: Page 
535
    535
  • Thumbnail: Page 
536
    536
  • Thumbnail: Page 
537
    537
  • Thumbnail: Page 
538
    538
  • Thumbnail: Page 
539
    539
  • Thumbnail: Page 
540
    540
  • Thumbnail: Page 
541
    541
  • Thumbnail: Page 
542
    542
  • Thumbnail: Page 
543
    543
  • Thumbnail: Page 
544
    544
  • Thumbnail: Page 
545
    545
  • Thumbnail: Page 
546
    546
  • Thumbnail: Page 
547
    547
  • Thumbnail: Page 
548
    548
  • Thumbnail: Page 
549
    549
  • Thumbnail: Page 
550
    550
  • Thumbnail: Page 
551
    551
  • Thumbnail: Page 
552
    552
  • Thumbnail: Page 
553
    553
  • Thumbnail: Page 
554
    554
  • Thumbnail: Page 
555
    555
  • Thumbnail: Page 
556
    556
  • Thumbnail: Page 
557
    557