A dataset containing the daily realized variance, and some of its lags, obtained from 1-minute close prices of the S\&P 500. Similar data has been used in the HAR model in Corsi (2009), the HARQ and SHARQ models in Bollerslev et al (2016) and the TVHARQ and TVSHARQ models in Casas et al (2018). The time period runs from Feb 1990 until Dec 2006.

Format

A data frame with 4264 rows and 6 variables.

Date

Daily data from Feb 1, 1990 until Dec 29, 2006 - without weekends and days off

RV

Daily realized variance at time t

RV_lag

Daily realized variance at time t-1

RV_week

Weekly average realized variance at time t-5

RV_month

Monthly average realized variance at time t-22

RQ_lag_sqrt

Daily squared root of the realized quarticity at time t-1

References

Bollerslev, T., Patton, A. J. and Quaedvlieg, R. (2016) Exploiting the errors: A simple approach for improved volatility forecasting. Journal of Econometrics, 192, 1-18.

Bollerslev, T., Tauchen, G. and Zhou, H. (2009) Expected stock returns and variance risk premia. The Review of Financial Studies, 22, 44-63.

Casas, I., Mao, X. and Vega, H. (2018) Reexamining financial and economic predictability with new estimators of realized variance and variance risk premium. Url= http://pure.au.dk/portal/files/123066669/rp18_10.pdf

Corsi, F. (2009) A simple approximate long-memory model of realized volatility. Journal of Financial Econometrics, 7, 174-196.