Forecasting International Affairs: An Empirical Test of a Markov Renewal Model.

Abstract

A major difficulty for designers of systems to forecast international affairs has been to allow the use of both observable data and subjective estimates. Under DARPA sponsorship, a novel approach has been developed by other contractors based upon a Bayesian stochastic model. The present report discusses an experimental test of the approach in an actual intelligence setting. In this experiment, both direct subject probabilistic forecasts and those generated by computer models performed well. There was some suggestion that the direct assessments might be better for short-term forecasts and that the computer models might be most valuable in longer-term forecasting (30 days and longer) in dynamic situations. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Jun 01, 1982
Accession Number
ADA115656

Entities

People

  • James O. Chinnis Jr.

Tags

Communities of Interest

  • C4I

DTIC Thesaurus Topics

  • Abstracts
  • Bayesian Inference
  • Classification
  • Computer Programs
  • Computers
  • Consortiums
  • Contracts
  • Cooperation
  • Delphi Method
  • Experimental Design
  • Observation
  • Plastic Explosives
  • Probability
  • Program Management
  • Security
  • Statistical Analysis
  • Supervision

Readers

  • Atmospheric Science/Meteorology
  • Systems Analysis and Design
  • Technical Research and Report Writing.

Technology Areas

  • AI & ML
  • AI & ML - Bayesian Inference