JMASM3: A Method for Simulating Systems of Correlated Binary Data
Article Sidebar
Published
Jan 5, 2002
Main Article Content
Todd C. Headrick
Southern Illinois University at Carbondale
Abstract
An efficient algorithm is derived for generating systems of correlated binary data. The procedure allows for the specification
of all pairwise correlations within each system. Intercorrelations between systems can be specified qualitatively.
The procedure requires the simultaneous solution of a system of equations for obtaining the threshold probabilities
to generate each system of binary data. A numerical example is provided to demonstrate that the procedure generates
correlated binary variables that yield correlations in close agreement with the specified population correlations.
Article Details
Issue
Section
Articles