Choosing Rolling or Expanding Windows for GARCH Volatility Models
Summary
The document compares rolling and expanding estimation windows for GARCH volatility forecasts. A rolling window emphasizes recent observations, which may help when volatility shifts between regimes. An expanding window keeps the full history and may capture longer-run volatility behavior; one answer also compares this approach with exponential smoothing, while noting that GARCH includes mean reversion.
The responses offer conflicting practitioner preferences rather than a settled result. One argues that older data can distort estimates during high-volatility periods, while the other expects the model to adapt to changes in average volatility over time. Both positions are conceptual, not supported here by a reported empirical comparison. The practical recommendation is to evaluate both window choices on the forecasting task at hand. The document does not specify window lengths, data, evaluation metrics, or a universal rule, and its discussion concerns volatility modeling rather than a particular trading strategy.
Key ideas
- Rolling estimation can emphasize recent volatility regimes.
- Expanding estimation retains the full return history and may reflect longer-run changes in volatility.
- GARCH captures time-varying volatility and mean-reversion effects.
- The responses disagree on which window is preferable, so compare forecast performance empirically.
Tags
Full text
# GARCH modeling - sliding or expanding window? # GARCH modeling - sliding or expanding window? In practice, when modeling volatility do people tend to use expanding or sliding windows to fit GARCH models? For example see rolling forecast generation vs recursive forecast generation in the Python arch package here: Arch Documentation In short, is it only useful to fit GARCH parameters on more recent data, or better to use the whole history of returns data to fit GARCH model to predict one/n step forward volatility? ## Answer by phdstudent (score 5, accepted) https://quant.stackexchange.com/a/38807 If you are just modelling volatility and not stochastic volatility of volatility then it should be better to use a sliding window. The reason is that volatility itself is time-varying and therefore an expanding window does not take into account regime shifts in volatility. The fact that volatility is time-varying is a stylized fact, two prominent references are: - Bloom (2009) - The Impact of Uncertainty Shocks - Bollerslev, Tauchen and Zhou (2009) - Expected Stock Returns and Variance Risk Premia Either the above you will see either regime shifts in volatility or time-varying volatility of volatility. This means that the unconditional mean for volatility that you get with an expanding window might severely impact negatively your estimates specially in bad times such as the financial crisis. In either case whether it is better to use an expanding window or a rolling window is an empirical question. I suggest you estimate both ways and check empirically what works better. This other question guides on how to empirically test the performance or Arch-type models. ## Answer by John (score 3) https://quant.stackexchange.com/a/38746 I tend to use an expanding window. The reason is that the GARCH model aims to capture time-varying volatility effects so if the average level has changed overtime, then hopefully the model will take this into account. By contrast, if you estimated a constant variance, then the prior history may be less relevant than the more recent history. In addition, GARCH can also be thought of as a model similar to exponential smoothing, though exponential smoothing does not have the mean-reversion effect that GARCH does. Exponential smoothing tends to be used with an expanding window rather than a sliding window.
Shown in full with attribution under the source's licence. Licence: CC BY-SA 4.0 (Stack Exchange)
This summary was written by Stratmill's research agent from the original; it is not a copy of the source.