Measuring equity risk premium and risk aversion in the US.
In our project, we estimated the time series of risk aversion using annual data for the U.S. We use the time varying parameter GARCH-M model, proposed by [Chou et al., 1992] for the estimation. The S&P 500 stock index was used as the market index; and constant maturity 10-year T-Bonds as well a...
Saved in:
| Main Authors: | , , |
|---|---|
| Other Authors: | |
| Format: | Final Year Project |
| Published: |
2008
|
| Subjects: | |
| Online Access: | http://hdl.handle.net/10356/10404 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Institution: | Nanyang Technological University |
| Summary: | In our project, we estimated the time series of risk aversion using annual data for the U.S. We use the time varying parameter GARCH-M model, proposed by [Chou et al., 1992] for the estimation. The S&P 500 stock index was used as the market index; and constant maturity 10-year T-Bonds as well as T-Bills yields were used to represent the risk-free rate. The excess return using T-Bonds covered the period from 1906 to 2005 (100 years worth of data). While, the excess return using T-Bills covered the period from 1921 to 2005.
We attempt to estimate and analyze the historical time series of risk aversion over a long time period using as long series data as possible. In the analysis, we want to test to see if the risk aversion is constant over time. We also want to compare our results with that of [Chou et al., 1992] to see if there are any significant differences. Since their study used monthly data and we use annual data, any difference could be due to the fact that the nature of risk aversion may depend on the investment horizon. |
|---|