FORECASTING CLAIM FREQUENCY BY USING FIRST-ORDER CPINAR MODEL
<p align="justify">Claim-frequency, besides claim-severity, is an important part of (insurance) claim. Forecasting claim-frequency can be determined by employing integer-valued autoregressive or INAR model. There are two aspects of such model: number of claim processed during certain...
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/26559 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | <p align="justify">Claim-frequency, besides claim-severity, is an important part of (insurance) claim. Forecasting claim-frequency can be determined by employing integer-valued autoregressive or INAR model. There are two aspects of such model: number of claim processed during certain period of time (survival) and number of claim arrived up to certain time (arrival); the latter is called innovation. In this thesis, we deal with innovation following compound-Poisson distribution. This represents aggregate claims. The resulting model is named as CPINAR; specifically we have used CPINAR-Poisson and CPINAR-logarithmic. Claimfrequency predicted by CPINAR model involves calculating conditional mean and unstraightforward probability. The method of estimation used are least squared and maximum. likelihood.<p align="justify"> |
|---|