Skip to main content
padlock icon - secure page this page is secure

Identifying the Causal Structure from the Correlation Matrix

Buy Article:

$106.34 + tax (Refund Policy)

The structure with the best posterior probability as calculated by the Cooper and Herskovits formula does not necessarily give the correct causal structure. There is a need to understand why the posterior probability structure sometimes gives incorrect structures. A new norm is identified that simplifies identification of the causal structure. In this research some theorems are proved to identify the causal structure. The aim of the research on which this article reports, was to place the first two theorems that this author proved about the norm, that gives an alternative to the Cooper and Herskovits algorithm, in the public domain. There are a number of theorems still not proven and other researchers can give valuable input if they follow the same approach. For a tree structure the best posterior probability structure gives the correct causal structure, however when v-structures are present there is often a discrepancy between the actual causal structure and the highest posterior probability structure. This article helps to clarify this situation and recommends an approach that should eventually lead to a better understanding of causal processes.
No Reference information available - sign in for access.
No Citation information available - sign in for access.
No Supplementary Data.
No Article Media
No Metrics

Keywords: Causal Structures from Cross Sectional Data Bayesian Belief Networks Probabilistic Network Models

Document Type: Research Article

Affiliations: Unisa School of Business Leadership, Janadel Street, Midrand, Gauteng, South Africa

Publication date: April 1, 2017

More about this publication?
  • ADVANCED SCIENCE LETTERS is an international peer-reviewed journal with a very wide-ranging coverage, consolidates research activities in all areas of (1) Physical Sciences, (2) Biological Sciences, (3) Mathematical Sciences, (4) Engineering, (5) Computer and Information Sciences, and (6) Geosciences to publish original short communications, full research papers and timely brief (mini) reviews with authors photo and biography encompassing the basic and applied research and current developments in educational aspects of these scientific areas.
  • Editorial Board
  • Information for Authors
  • Subscribe to this Title
  • Ingenta Connect is not responsible for the content or availability of external websites
  • Access Key
  • Free content
  • Partial Free content
  • New content
  • Open access content
  • Partial Open access content
  • Subscribed content
  • Partial Subscribed content
  • Free trial content
Cookie Policy
X
Cookie Policy
Ingenta Connect website makes use of cookies so as to keep track of data that you have filled in. I am Happy with this Find out more