ISSN:
1432-5225
Source:
Springer Online Journal Archives 1860-2000
Topics:
Agriculture, Forestry, Horticulture, Fishery, Domestic Science, Nutrition
,
Mechanical Engineering, Materials Science, Production Engineering, Mining and Metallurgy, Traffic Engineering, Precision Mechanics
Notes:
Summary Inherent in most simulation processes is a mechanism to sample from known probability distributions. This is most often accomplished with the aid of pseudo-random generation systems. Though, these generators produce sets of numbers which are usually statistically indistinguishable from a uniform distribution, the actual distribution of any individual one of these data sets exhibit peaks and valleys which, when used in simulations, somewhat misrepresent the desired probability distribution. A stratified approach to fulldistribution sampling is presented which represents a marked improvement over random number generated sampling in certain types of simulation procedures.
Type of Medium:
Electronic Resource
URL:
http://dx.doi.org/10.1007/BF00349915