PREDICTION OF COPULA-BASED AGGREGATE RISK MEASURE IN INVESTMENT AND INSURANCE
Aggregate risk is an aggregation of single risk either independent or dependent. In the thesis, aggregate risk is constructed from two dependent random risk variables. The dependence between two random risk variables can be determined by dependence structures and properties of joint distribution....
Saved in:
| Main Author: | |
|---|---|
| Format: | Theses |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/39124 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Aggregate risk is an aggregation of single risk either independent or dependent. In
the thesis, aggregate risk is constructed from two dependent random risk variables.
The dependence between two random risk variables can be determined by
dependence structures and properties of joint distribution. However, not all
distribution have properties of joint distribution so, the Copula model is introduced
to construct properties of joint distribution. Aggregate risk is widely used in
finance, such as investment and insurance. In the investment sector, the aggregate
formed from sum of single risk return on assets that is modeled using the volatility
model Generalized Autoregressive Conditionally Heteroscedastic (GARCH).
Then, in the insurance sector, the aggregate risk formed from sum of single risk
claim severity that is modeled using Autoregressive Conditional Amount (ACA).
Aggregate risk must be quantified through a risk measure, such as Value-at-Risk
(VaR). Furthermore, the VaR accuracy test is simulated for investment and
insurance. The test is useful for choosing the best aggregate risk model in
determining the prediction of aggregate VaR either return or claim severity. |
|---|