Springer Nature is making SARS-CoV-2 and COVID-19 research free. View research | View latest news | Sign up for updates

Clusterwise linear least absolute deviations regression

Algorithmus. Klassenweise Regression bei der Methode der kleinsten absoluten Abweichungen

  • 68 Accesses

  • 8 Citations


A FORTRAN subroutine implementation for this purpose is given.


Die Implementation einer FORTRAN-Subroutine für diesen Zweck wird angegeben.

This is a preview of subscription content, log in to check access.


  1. [1]

    Armstrong, R. D., Frome, E. L., Kung, D. S.: A revised simplex algorithm for the absolute deviation curve fitting problem. Commun. Statist.-Simula. Computa.B8, 175–190 (1979).

  2. [2]

    Peters, U., Willms, C.: Up- and down-dating procedures for linearL 1 regression. OR Spektrum5, 229–239 (1983).

  3. [3]

    Späth, H.: Algorithm 39: Clusterwise linear regression. Computing22, 367–373 (1979).

  4. [4]

    Späth, H.: Correction to algorithm 39: Clusterwise linear regression. Computing26, 275 (1981).

  5. [5]

    Späth, H.: Algorithm 48: A fast algorithm for clusterwise linear regression. Computing29, 175–181 (1982).

  6. [6]

    Späth, H.: Cluster dissection and analysis: Theory, FORTRAN programs, examples, Chichester: Horwood 1985.

  7. [7]

    Späth, H.: Clusterwise linear least squares versus least absolute deviations regression: a numerical comparison for a case study. In: Classification as a Tool of Research, Proceedings of the 9th Annual Meeting of the German Classification Society (Gaul, W., Schader, M., eds.). Amsterdam: North Holland 1986.

Download references

Author information

Rights and permissions

Reprints and Permissions

About this article

Cite this article

Späth, H. Clusterwise linear least absolute deviations regression. Computing 37, 371–377 (1986). https://doi.org/10.1007/BF02251095

Download citation

AMS Subject Classifications

  • 62J05
  • 65F20
  • 62H30

Key words

  • L 1 regression
  • clusterwise regression