Skip to content
All library documents

Finding Robust Intraday Realized Volatility Estimators for SPY

Article Quant Q&A · Author: nan
Read the original

Summary

The document asks how to estimate realized volatility over 15- and 30-minute intervals for SPY using observations sampled each second. The researcher is looking for a nonparametric measure that remains robust to market microstructure noise and jumps, noting that much of the literature they found focuses on daily volatility.

The response recommends the R package highfrequency as a source of tools, references, and methodology. It does not identify a particular estimator, sampling scheme, or parameter choice, and it offers no comparison or empirical result for the requested intraday horizons. The package recommendation is therefore a starting point for research rather than a complete procedure; the appropriate estimator still depends on the data and the desired treatment of noise and jumps.

Key ideas

  • The question concerns realized volatility estimates over intraday horizons using second-level SPY data.
  • The researcher seeks methods that address market microstructure noise and jumps.
  • The response recommends the highfrequency R package for methods and references.
  • No specific estimator, sampling frequency, or empirical validation is provided.

Tags

EquitiesVolatilityStatisticsMarket microstructure
Full text
# How to compute the realised intraday volatility?


# How to compute the realised intraday volatility?












I'm in the position to calculate a non-parametric volatility estimator for 15 and 30 minutes intervals of the SPY. I got data sampled on second resolution. However, I checked plenty of papers but, as far as I understood them, all of the proposed models are solely applied to measure daily volatility. All of the proposed kernels or subsampling methodologies to deal with microstructure noise and/or jumps are estimated to get daily volatility. How do I estimate a robust realized volatility measure for the stated intraday frequencies?

## Answer by cJc (score -1)

https://quant.stackexchange.com/a/31868

Have a look at the following R package:

https://www.rdocumentation.org/packages/highfrequency/versions/0.4?

I believe it has all the tools you need and good references to papers and methodology.

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.