Extension of the Iterative Proportional Fitting Procedure and Its Evaluation Using Agent-Based Models

Conference paper
First Online:
Part of the Agent-Based Social Systems book series (ABSS, volume 10)

Abstract

The iterative proportional fitting procedure (IPFP) is a well-known algorithm as the RAS method to compilers of national accounts. In this study, an agent-based model is used to implement the IPFP algorithm. It makes extensions of the algorithm easy. A method that deals with inconsistent marginal values by modifying the adjusting factor of the classical IPFP is proposed. Evaluation of the method is attempted using an agent-based model. The proposed method shows good performance when the lack of information disables the use of the classical IPFP.

Keywords

Agent-based model Adjustment factor IPFP RAS method 
This is a preview of subscription content, log in to check access.

References

  1. 1.
    Deming WE, Stephan FF (1940) On a least squares adjustment of a sampled frequency table when the expected marginal totals are known. Ann Math Stat 11(4):427–444MathSciNetCrossRefGoogle Scholar
  2. 2.
    Pukelsheim F (2012) An L1-analysis of the iterative proportional fitting procedure. Preprints-Herausgeber: Institut für Mathematik der Universität Augsburg 2012-02Google Scholar
  3. 3.
    Saito S (1998) Extensions of iterative proportional fitting procedure and I-projection modeling. Kyushu University Press, Fukuoka, JapanGoogle Scholar

Copyright information

© Springer Japan 2013

Authors and Affiliations

  1. 1.Division of Policy and Planning Sciences, Faculty of Engineering, Information and SystemsUniversity of TsukubaTsukubaJapan

Personalised recommendations