Lassoing the Har Model: A Model Selection Perspective on Realized Volatility Dynamics
54 Pages Posted: 14 Oct 2013
Date Written: October 14, 2013
Realized volatility computed from high-frequency data is an important measure for many applications in finance. However, its dynamics are not well understood to date. Recent notable advances that perform well include the heterogeneous autoregressive (HAR) model which is economically interpretable and easy to estimate. It also features good out-of-sample performance and has been extremely well received by the research community.
We present a data driven approach based on the absolute shrinkage and selection operator (lasso) which should identify the aforementioned model. We prove that the lasso indeed recovers the HAR model asymptotically if it is the true model, and we present Monte Carlo evidence in finite sample. The HAR model is not recovered by the lasso on real data. Moreover, we provide empirical evidence that there is a break in structure during the financial crisis. These results bring into question the appropriateness of the HAR model for realized variance. Finally, in an out-of-sample analysis we show equal performance of the HAR model and the lasso approach.
Keywords: Realized Volatility, Heterogeneous Autoregressive Model, Lasso, Model Selection
JEL Classification: C58, C63, C49
Suggested Citation: Suggested Citation