Book contents
- Frontmatter
- Contents
- Preface to first edition
- Preface to second edition
- 1 Introduction and mathematical preliminaries
- 2 Elementary probability
- 3 Random variables and their distributions
- 4 Location and dispersion
- 5 Statistical distributions useful in general insurance work
- 6 Inferences from general insurance data
- 7 The risk premium
- 8 Experience rating
- 9 Simulation
- 10 Estimation of outstanding claim provisions
- 11 Elementary risk theory
- References
- Solutions to exercises
- Author index
- Subject index
8 - Experience rating
Published online by Cambridge University Press: 05 June 2012
- Frontmatter
- Contents
- Preface to first edition
- Preface to second edition
- 1 Introduction and mathematical preliminaries
- 2 Elementary probability
- 3 Random variables and their distributions
- 4 Location and dispersion
- 5 Statistical distributions useful in general insurance work
- 6 Inferences from general insurance data
- 7 The risk premium
- 8 Experience rating
- 9 Simulation
- 10 Estimation of outstanding claim provisions
- 11 Elementary risk theory
- References
- Solutions to exercises
- Author index
- Subject index
Summary
Summary. In this chapter we explain the need for experience rating and introduce some elementary credibility theory which finds application in this area. We also show how Bayes' methods can be used to update estimates of a claim frequency rate in the light of experience, and examine briefly a particular form of experience rating: no claim discount (NCD).
Introduction
In section 5.9 we saw that, for most classes of general insurance, many possible sources of heterogeneity of risk exist. A premium rate based on the observed claim rate for a heterogeneous portfolio might prove quite inadequate if, as is likely, the mix of risks were to change. To reduce this danger, policies are usually grouped according to the different levels of the various risk factors involved. Claim frequency rates and premiums for the different groups are then calculated. This approach to the problem is called group rating. Multivariate methods can also be used to estimate the effects of the various levels of each risk factor on the claim frequency rate and premium.
Even when policies are grouped according to the different levels of various relevant risk factors, the residual heterogeneity within the groups is often still considerable. Many policies will have underlying claim frequency rates near the mean rate for the group. Some, however, will have considerably higher underlying rates, and some considerably lower, and it is desirable that we distinguish between these. We may attempt further subdivision of the groups using additional risk factors or additional intermediate levels of existing factors.
- Type
- Chapter
- Information
- Introductory Statistics with Applications in General Insurance , pp. 151 - 176Publisher: Cambridge University PressPrint publication year: 1999