Skip to main content
Log in

A credibility approach to the munich chain-ladder method

Ein Credibility-Ansatz für die Munich Chain-Ladder Methode

  • Published:
Blätter der DGVFM

Summary

We give a credibility approach to the Munich chain-ladder (MCL) method introduced by Quarg & Mack [8]. If we use a credibility approach (best affine-linear predictors) to estimate claims reserves, the model assumptions underlying the MCL method can be reduced to the usual model assumptions of the classical chain-ladder model of Mack [5]. This shows that the MCL model defined by Quarg & Mack [8] is a natural extension of the classical Mack model [5] in a linear Bayesian framework, and that MCL estimators are locally optimal linear predictors in this context.

Zusammenfassung

Wir betrachten einen auf der Credibility-Theorie basierenden Ansatz, der zur Munich Chain-Ladder Methode (MCL-Methode) von Quarg & Mack [8] führt. Die Verwendung von optimalen affin-linearen Prädiktoren zur Prognose der Schadenreserve ermöglicht die Einschränkung der Annahmen des MCL-Modells [8] auf die wohlbekannten Annahmen des Modells von Mack [5]. Dieser Zugang zeigt, dass das MCL-Modell von Quarg & Mack [8] innerhalb der linear Bayes-Theorie als eine natürliche Erweiterung des Modells von Mack [5] aufgefasst werden kann und die Schätzer der MCL-Methode lokal optimale lineare Prädiktoren sind.

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

Literatur

  1. Benktander, G. (1976). An approach to credibility in calculating IBNR for casualty excess reinsurance.The Actuarial Review, April 1976, 7.

  2. Brockwell, P. J. and Davis, R. A. (1991).Time Series: Theory and Methods. Springer-Verlag, Berlin.

    Google Scholar 

  3. Bühlmann, H. and Gisler, A. (2005).A Course in Credibility Theory and its Applications. Springer-Verlag, Berlin.

    MATH  Google Scholar 

  4. Halliwell, L. J. (1997). Conjoint prediction of paid and incurred losses.CAS Forum Summer 1997, vol. 1, 241–379.

    Google Scholar 

  5. Mack, T. (1993). Distribution-free calculation of the standard error of Chain Ladder reserve estimates.Astin Bulletin 23, 2, 213–225.

    Article  Google Scholar 

  6. Mack, T. (2000). Credible claims reserves: The Benktander method.ASTIN Bulletin 30, 2, 333–347.

    Article  MATH  MathSciNet  Google Scholar 

  7. Neuhaus, W. (1992). Another pragmatic loss reserving method or Bornhuetter/Ferguson revisited.Scandinavian Actuarial Journal 1992, 151–162.

  8. Quarg, G., Mack, T. (2004). Munich Chain Ladder.Blätter der DGVFM, Band XXVI, 597–630.

    Article  Google Scholar 

  9. Vylder De, F. (1982). Estimation of IBNR claims by credibility theory.Insurance: Mathematics and Economics 1, 35–40.

    Article  MATH  Google Scholar 

  10. Witting, T. (1987). Kredibilitätsschätzungen für die Anzahl IBNR-Schäden.Blätter der DGVFM, Band XVIII, 45–58.

    Google Scholar 

Download references

Author information

Authors and Affiliations

Authors

Corresponding author

Correspondence to Michael Merz.

Rights and permissions

Reprints and permissions

About this article

Cite this article

Merz, M., Wüthrich, M.V. A credibility approach to the munich chain-ladder method. Blätter DGVFM 27, 619–628 (2006). https://doi.org/10.1007/BF02809220

Download citation

  • Issue Date:

  • DOI: https://doi.org/10.1007/BF02809220

Keywords

Navigation