統計学輪講（第３３回）

日時      2009年12月22日(火)    15時～16時40分
場所      経済学部新棟３階第３教室
講演者    松井 宗也 (日本学術振興会)
演題      Prediction in a Poisson cluster model

概要

In a non-life insurance context the prediction of the
number and amount of payments in future time are essential.
In this talk, we consider a Poisson cluster model as a model for
claim reserves, and consider some prediction procedure.
In the model, after each claim arrival time, which is modeled by a point
of a homogeneous Poisson process, we start
a cluster process which represents the number or amount
of payments triggered by the arrival of a claim
in a portfolio. The cluster process is a
Levy or truncated Poisson process.

Explicit expressions for the prediction and the corresponding
prediction error are given .
This is joint work with T. Mikosch.