Skip to main content
Log in

A criterion for selecting log-linear models for contingency tables

  • Theoretical Papers
  • Published:
Operations-Research-Spektrum Aims and scope Submit manuscript

Summary

A new discrepancy, the Gauss discrepancy of the logarithms of frequencies, is introduced for the selection of log-linear models for contingency tables. Under the assumption of Poisson sampling the loglinear model becomes orthogonal for this discrepancy: the model selection criterion is the sum of the contributions (to the criterion) of the effects in the model. It is, therefore, sufficient for model selection to compute the contributions of the effects in the saturated model. The selected model contains then all effects with negative contributions. It is not necessary to recompute the value of the criterion for all possible models. Two examples are given.

Zusammenfassung

Für die Auswahl log-linearer Modelle für Kontingenztafeln wird eine neue Diskrepanz eingeführt, die Gauss Diskrepanz zwischen den Logarithmen der Häufigkeiten. Unter der Annahme, daß die beobachteten Häufigkeiten Poisson-verteilt sind, wird das loglineare Modell für diese Diskrepanz orthogonal: das Modellauswahlkriterium ist die Summe der Beiträge (zum Kriterium) der Effekte im Modell. Zur Auswahl eines Modells genügt es also, die Beiträge der einzelnen Effekte des gesättigten Modells getrennt zu berechnen. Das ausgewählte Modell enthält dann alle Effekte mit negativen Beiträgen. Es ist nicht notwendig, den Wert des Kriteriums für jedes mögliche Modell neu zu berechnen. Zwei Beispiele werden durchgerechnet.

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

Access this article

Price excludes VAT (USA)
Tax calculation will be finalised during checkout.

Instant access to the full article PDF.

Similar content being viewed by others

References

  1. Bishop Y, Fienberg S, Holland P (1975) Discrete multivariate analysis: theory and practice. MIT Press, Cambridge, Mass. London

    Google Scholar 

  2. Fahrmeir L, Hamerle A (1981) Kategoriale Regression in der betrieblichen Planung. Z Oper Res B25:63–78

    Google Scholar 

  3. Fienberg S (1980) The analysis of cross-classified categorical data. 2nd Edn. MIT Press, Cambridge Massachusetts London

    Google Scholar 

  4. Goodman L (1970) The multivariate analysis of qualitative data: interactions among multiple classifications. J Am Stat Ass 65:226–256

    Google Scholar 

  5. Goodman L (1971) The analysis of multidimensional contingency tables: stepwise procedures and direct estimation methods for building models for multiple classifications. Technometrics 13:33–61

    Google Scholar 

  6. Linhart H, Zucchini W (1986) Model selection. Wiley, New York

    Google Scholar 

  7. Pearson ES, Hartley HO (1972) Biometrika tables for statisticians, vol II. University Press, Cambridge

    Google Scholar 

  8. Upton G (1978) The analysis of cross-tabulated data. Wiley, New York

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Rights and permissions

Reprints and permissions

About this article

Cite this article

Böker, F. A criterion for selecting log-linear models for contingency tables. OR Spektrum 10, 167–172 (1988). https://doi.org/10.1007/BF01740511

Download citation

  • Received:

  • Accepted:

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF01740511

Keywords

Navigation