VALUE-AT-RISK PREDICTION USING EXPECTILES
Value at Risk (VaR) has become the standard measure of risk employed by finan- cial institutions for both internal and regulatory purposes. VaR is defined as an estimation of the largest loss that may occur in the span of time or a certain time period forecasted by some chance level. Defining the...
Saved in:
| Main Author: | |
|---|---|
| Format: | Final Project |
| Language: | Indonesia |
| Online Access: | https://digilib.itb.ac.id/gdl/view/17906 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Institut Teknologi Bandung |
| Language: | Indonesia |
| Summary: | Value at Risk (VaR) has become the standard measure of risk employed by finan-
cial institutions for both internal and regulatory purposes. VaR is defined as an
estimation of the largest loss that may occur in the span of time or a certain time
period forecasted by some chance level. Defining the conventional VaR likely more
related to the level while defining new chance to say more associated with large
losses. The value of loss tends to change over time, therefore the VaR calculation is
done using the Autoregressive (AR) model. In this final project, the author shows
the two definitions of VaR calculation: using quantile definition and using expectiles
definition from generated data. The results showed the same value of VaR for the
value of loss and at a certain intervals that are small enough. |
|---|