MULTIVARIATE UNIFORM RANDOM NUMBERSName:
LET Y = <dist> RANDOM NUMBERS FOR I = 1 1 N
LET Y = LOC + SCALE*Y
Multivariate distributions, however, generally require matrix operations. For this reason, random numbers for multivariate distributions each have their own unique syntax. Although you can generate P columns of uniform random numbers, this does take into account any correlation between the variables (i.e., they are independent).
To generate correlated uniform random numbers, Dataplot generates correlated multivariate random numbers and then takes the normal cumulative distribution function of these numbers. This algorithm is from Gentle (2003) "Random Number Generation and Monte Carlo Methods".
For details on how to generate uncorrelated multivariate uniform random numbers, enter HELP INDEPENDENT UNIFORM RANDOM NUMBERS.
where <sigma> is a variance-covariance matrix from a multivariate normal distribution;
<n> is a number or parameter specifying the desired number of rows;
and <mat> is a matrix where the resulting multivariate independent uniform random numbers are stored.
Dataplot determines the number of columns to generate from
the number of rows in the
dimension 100 columns . READ MATRIX SIGMA 1.0 0.5 0.5 1.0 END OF DATA LET N = 1000 . CHARACTER . CHARACTER JUSTIFICATION LEBO LINE BLANK . LET M = MULTIVARIATE UNIFORM RANDOM NUMBERS SIGMA N . PLOT M1 VS M2
Date created: 2/3/2004