Forecasting Crashes with a Smile
Event details
| Date | 21.03.2025 |
| Hour | 11:45 › 13:00 |
| Speaker | Ian Martin - LSE |
| Location |
UniL Campus, Room Extra 126
|
| Category | Conferences - Seminars |
| Event Language | English |
We derive option-implied bounds on the probability of a crash in an individual stock and argue that the lower bound should be close to the truth a priori. Empirically, the lower bound successfully forecasts crashes both in and out of sample; and it outperforms models based on stock characteristics previously studied in the literature. In a multivariate regression, a one standard deviation increase in the bound raises the predicted crash probability by 3 percentage points, whereas a one standard deviation increase in the next most important predictor (a measure of short interest) raises the predicted probability by only 0.3 percentage points.
Links
Practical information
- Informed public
- Free
Contact
- sophie.cadenakauz@epfl.ch