Information graphs for binary predictors

G Hughes, N McRoberts, FJ Burnett

Research output: Contribution to journalArticlepeer-review

5 Citations (Scopus)
5 Downloads (Pure)

Abstract

Binary predictors are used in a wide range of crop protection decisionmaking applications. Such predictors provide a simple analytical apparatus for the formulation of evidence related to risk factors, for use in the process of Bayesian updating of probabilities of crop disease. For diagrammatic interpretation of diagnostic probabilities, the receiver operating characteristic is available. Here, we view binary predictors from the perspective of diagnostic information. After a brief introduction to the basic information theoretic concepts of entropy and expected mutual information, we use an example data set to provide diagrammatic interpretations of expected mutual information, relative entropy, information inaccuracy, information updating, and specific information. Our information graphs also illustrate correspondences between diagnostic information and diagnostic probabilities.
Original languageEnglish
Pages (from-to)9 - 17
Number of pages9
JournalPhytopathology
Volume105
Issue number1
DOIs
Publication statusFirst published - 2015

Bibliographical note

1023370

Keywords

  • Diagnosis
  • Disease management
  • Entropy
  • Information theory

Fingerprint Dive into the research topics of 'Information graphs for binary predictors'. Together they form a unique fingerprint.

Cite this