Frequency and Severity Models

Select loss models from the insurance question, observation process, and tail—not from a distribution list.

Frequency and Severity Models

Probability models turn incomplete claim experience into statements about unobserved losses. The right starting point is the insurance process:

exposureclaim count Nseverities X1,,XNS=i=1NXi.\text{exposure}\longrightarrow \text{claim count }N \longrightarrow \text{severities }X_1,\ldots,X_N \longrightarrow S=\sum_{i=1}^{N}X_i.

Model-selection map

QuestionData unitFirst modelsEssential complication
How large is an ordinary positive claim?one ground-up lossGamma, lognormaldeductible, limit, inflation
How heavy is the extreme tail?threshold exceedance or event lossPareto, GPDthreshold uncertainty, dependence
How many claims occur?count plus exposure periodPoisson, negative binomialexposure, heterogeneity, seasonality
Which model predicts unseen claims?training and validation sampleslikelihood-based candidatescensoring, truncation, parameter uncertainty
Why are there several claim populations?latent or observed groupsmixture/hierarchical modelidentifiability and changing mix

No distribution is “the insurance distribution.” A body model that predicts typical claims well can fail at reinsurance layers; a tail model can waste information if fitted to every small claim.

The four objects to report

For a loss XX:

ObjectDefinitionInsurance use
CDFF(x)=P(Xx)F(x)=P(X\le x)probability a loss is no larger than xx
SurvivalFˉ(x)=1F(x)=P(X>x)\bar F(x)=1-F(x)=P(X>x)attachment and exceedance probability
QuantileQ(p)=F1(p)Q(p)=F^{-1}(p)VaR and scenario thresholds
Stop-loss meanE[(Xd)+]=dFˉ(x)dxE[(X-d)_+]=\int_d^\infty\bar F(x)\,dxexpected unlimited layer loss above dd

The mean alone is not enough. Two models can share E[X]E[X] and imply radically different high quantiles and reinsurance costs.

Observation comes before fitting

For every sample, label whether losses are:

  • ground-up, insurer-paid, or reinsurer-paid;
  • exact, right-censored at a limit, or truncated below a reporting threshold;
  • nominal or adjusted to a common price level;
  • per claim, occurrence, policy, claimant, or coverage;
  • independent observations or claims clustered by event/policyholder.

The severity pages begin with ordinary positive losses, tail models focus on extremes, count models use exposure, fitting respects the observation mechanism, and mixtures represent heterogeneity.

A compact analysis protocol

  1. Define the target random variable and decision.
  2. Reconcile and visualise raw and transformed data.
  3. Choose several plausible models from mechanism and support.
  4. Fit using the correct likelihood.
  5. check centre, tail, calibration, and held-out prediction separately.
  6. quantify parameter and model sensitivity.
  7. apply policy and reinsurance terms only on the stated loss basis.
In this course, Poisson, Gamma, and Pareto name distributions; frequency, severity, survival, and hazard name concepts. Symbols are defined locally because parameterisations differ across textbooks and software.
Copyright © 2026