Structure and Distance of Logical Patterns.

Abstract

The logical patterns defined in this report are matrices whose columns are random variables with very few discrete realizations on a nominal scale; e.g., responses 0 - 1 - 3 could be different hair colors. It is assumed that all the variables are influenced by a few major events producing the pattern. Rows are assumed to be either independent or to show auto-correlation of log 1, including, e.g., the Markov chain dependence. A Lancaster scaling technique is used for translating the nominal responses; a factor analysis (latent class) model is used to account for the influence of major events. Numerical examples, based upon computer runs, are presented for illustration. (Author)

Document Details

Document Type
Technical Report
Publication Date
May 01, 1970
Accession Number
AD0728427

Entities

People

  • H. I. Patel

Organizations

  • University of Georgia

Tags

DTIC Thesaurus Topics

  • Computers
  • Data Science
  • Factor Analysis
  • Information Science
  • Markov Chains
  • Mathematics
  • Probability
  • Random Variables
  • Stochastic Processes

Readers

  • Control Systems Engineering.
  • Mathematical Modeling and Probability Theory.
  • Organizational Psychology.