Evidence on EGARCH Forecast Bias and Volatility Model Comparisons
Summary
The document asks whether EGARCH volatility forecasts are biased and seeks a published academic source supporting that claim. It identifies a preprint on bias correction for EGARCH estimators and a published study of finite-sample properties of EGARCH maximum-likelihood and quasi-maximum-likelihood estimators. The response points to the latter as a potentially useful source but does not report its findings or establish that EGARCH forecasts themselves are biased.
A related answer cites a forecast comparison by Hansen and Lunde. Its quoted finding is that standard GARCH was not outperformed by more complex models for exchange rates, while models that account for leverage performed better for IBM returns. This comparison concerns relative forecasting performance across assets, not proof of EGARCH forecast bias. The document therefore offers references and a qualification rather than a conclusive recommendation against EGARCH; readers would need to consult the cited papers to assess their methods and results.
Key ideas
- The question concerns possible bias in EGARCH volatility forecasts and seeks published evidence.
- A cited 1996 study examines finite-sample properties of EGARCH maximum-likelihood and quasi-maximum-likelihood estimators.
- The document does not provide that study's results, so it cannot confirm the claimed bias.
- A separate comparison reports that model performance depends on the asset and whether leverage effects are represented.
- Relative performance evidence does not by itself prove that EGARCH forecasts are biased.
Tags
Full text
# References for biased forecasts from EGARCH # References for biased forecasts from EGARCH A few months ago I've read somewhere that although the exponential GARCH model may lead to higher BIC values in comparison to other extensions of the GARCH family (GARCH, GJR-GARCH, TGARCH, ...), volatility forecasting under this model may lead to biased results. I'm trying to find a trustworthy source (an academic paper) which could back this, but so far I've found - this Matlab page which indirectly tells me that results are biased, - this 2010 working paper which hasn't been published in any journal, and - some bachelor/master theses that report this info without backing it with an academic source. And as you may imagine, I can't (or better, I don't want to) quote other students' theses in my own thesis. Do you know of any published work which proves this claim? Or a reliable source which suggests why the EGARCH shouldn't be used for forecasting? ## Answer by Richard Hardy (score 0, accepted) https://quant.stackexchange.com/a/29541 I found a couple of papers mentioning bias of EGARCH: - Demos, Antonis, and Dimitra Kyriakopoulou. "Bias correction of ML and QML estimators in the EGARCH (1, 1) model." Preprint (2010). - Deb, Partha. "Finite sample properties of maximum likelihood and quasi-maximum likelihood estimators of EGARCH models." Econometric Reviews 15.1 (1996): 51-68. The first one is the same as you mention, so it is of no extra use to you. Probably the second one could be more useful. Unfortunately, I do not have access to it, so I cannot see what is inside. ## Answer by Robert (score 0) https://quant.stackexchange.com/a/29538 This does nor address your question directly, but is somehow related "We find no evidence that a GARCH(1,1) is outperformed by more sophisticated models in our analysis of exchange rates, whereas the GARCH(1,1) is clearly inferior to models that can accommodate a leverage effect in our analysis of IBM returns." Peter R. Hansen, Asger Lunde, A forecast comparison of volatility models: does anything beat a GARCH(1,1)? JAE, Volume 20, Issue 7, December 2005, Pages 873–889
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.