Showing papers on "Stochastic simulation published in 1972"

Stochastic Differential Equations and Models of Random Processes

Abstract: 1. Description of a desirable model Let us suppose that we are investigating a system whose state can be adequately specified by n real numbers x1, , x'. We shall suppose that by some acceptable scientific theory it is predicted that, in the absence of disturbances from outside the system, the xi develop in time in accordance with certain differential equations, (1.1) xi = ~~~~~~gio (t, x), i = ,**,n. If there are disturbances or noises, n1(t), . nr(t), the underlying theory of such systems will often permit us to conclude that

Some Important Distributions

Abstract: This chapter presents some properties of normally distributed random variables and also derives certain distribution functions that are important in statistics. It presents a proof of theorem for the distribution of the sum of independent, absolutely continuous random variables. In addition of independent normal random variables, one considers the two independently and normally distributed random variables X 1 and X 2 , and admits the possibility that their means and variances are different. The Chi-Square distribution discusses the determination of the distribution function of the sum of squares of independent normal random variables. This chapter also presents a proof for Student's distribution.

A stochastic simulation study of a rank-like test for dispersion which is distribution-free under location differences

Abstract: The existing rank tests for dispersion require the assumption that population locational differences are known in order to be distribution-free. In this paper we consider a rank-like test for dispersion which requires the samples to be broken into random subsets. Dispersion statistics including intra-pair differences, variances, and ranges are computed for each subset and then the Wilcoxon rank test is applied to these statistics for testing dispersion. A stochastic simulation study is summarized which investigates best subset size, dispersion statistic, and power relative to the usual F-test and one of the more popular rank tests

Queuing simulation using a random number generator

Abstract: Among the system performance predictive techniques available to the systems engineer are those of theoretical analysis and simulation. One method of simulation uses the random number generator to simulate the probability distribution of events. Introduced are principles of random number generator simulation together with examples, the results of which are compared with theoretical results.

Two remarks on the simulation of random variables

Abstract: A METHOD, more economic than the standard method, is described for simulating random variables with density e − x , x > 0. Simulation formulae for the beta distribution are obtained.

The Two-Machine Flow-Shop with Random Processing Times,

Abstract: : The authors consider the problem of sequencing n jobs in a simple two-machine flow-shop with the objective of finding a schedule with stochastically smallest makespan. Results are derived under a special stochastic structure for the processing time distributions. (Author)

Finite-time-averaged power spectra and signal energy distribution in time and frequency (Corresp.)

Abstract: In response to a recent paper, this correspondence points out the difficulty of applying the concept of the energy distribution in time and frequency of deterministic signals to random signals and finite-time-averaged power spectra. For deterministic signals, an appropriately defined finite-time spectrum will indicate the frequency band within which the signal energy is concentrated at a particular time. However, it does not appear meaningful to apply such concepts to finite-time averages of random processes since taking sample averages would typically destroy any time-frequency distribution of the energy perhaps found in an individual sample of the process.