[this page | pdf | references | back links]
Backtesting can be thought of as a short-hand way of seeking
to working out whether some sort of forecasting approach might work in the
future without actually having to wait for the future to arrive. In essence we
develop algorithms that identify what results our models would have generated
had we been running them at different points in time in the past, and we work
out how well they would have subsequently performed. It is particularly
important to be aware of the scope for ‘look-back bias’ in any such exercises.
Backtesting can be applied to many different types of model in quantitative
finance, including risk models and return forecasting models.
2. Backtesting of risk
3. In-sample versus
4. Testing backtest
Contents | Next