EVALUASI MODEL SIMULASI HISTORIS VALUE AT RISK PORTFOLIO DENGAN METODE CHRISTOFFERSEN
| Main Authors: | , Maryanto, , Dr. Abdurakhman, S.Si, M.Si. |
|---|---|
| Format: | Thesis NonPeerReviewed |
| Terbitan: |
[Yogyakarta] : Universitas Gadjah Mada
, 2014
|
| Subjects: | |
| Online Access: |
https://repository.ugm.ac.id/128467/ http://etd.ugm.ac.id/index.php?mod=penelitian_detail&sub=PenelitianDetail&act=view&typ=html&buku_id=68814 |
Daftar Isi:
- According to Christoffersen (1998), the property of a good VaR model are correct unconditional coverage, correct independence test and correct conditional coverage. Unconditional coverage test calculate how much violations exceed the VaR. If average of violations exceeded the percentage of VaR value, so it is called bad model. Independence test calculate how much violations clustering. If a model VaR has much violations clustering, so it is called bad model, because the risk of bankruptcy would be much higher than if the violations came scattered randomly through time. Conditional coverage test is simultaneously testing both unconditional coverage and independence test. Backtesting base on Christoffersen method different way with Kupiec method. Kupiec method only test on unconditional coverage, so Christoffersen method more complete than Kupiec method.