Long Memory, Realized Volatility and Heterogeneous Autoregressive Models

Baillie, Richard T.; Calonaci, Fabio; Cho, Dooyeon; Rho, Seunghwa

doi:10.1111/jtsa.12470

Cited by 32 publications

(12 citation statements)

References 65 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In future work, we would like to examine this in more detail by decomposing the effect of each variable on the RV forecast improvement. Furthermore, considering Baillie et al (2019), there may be room to extend our model, taking into account the long memory process. Chen et al (2018) and Ma et al (2019) are one of the helpful existing researches to expand our random forest based model to integrate long short-term memory process.…”

Section: Discussionmentioning

confidence: 99%

“…On the contrary, most RV forecasting modeling is expanded based on the ARFIMA modeling framework (Andersen et al 2001) or the HAR modeling framework (Corsi 2009). Baillie et al (2019) assess the separate roles of fractionally integrated long memory models, extended HAR models and time varying parameter HAR models. According to Baillie et al (2019), their experimental results suggest that RV series are quite complex and can involve both HAR components and long memory components.…”

Section: Literature Review Of Volatility Forecasting Modelsmentioning

confidence: 99%

“…Baillie et al (2019) assess the separate roles of fractionally integrated long memory models, extended HAR models and time varying parameter HAR models. According to Baillie et al (2019), their experimental results suggest that RV series are quite complex and can involve both HAR components and long memory components. Recently, as we noted in the previous section, Watanabe (2020) reports that various previous studies have followed Corsi (2009), expanding and generalizing the HAR model in many directions.…”

Section: Literature Review Of Volatility Forecasting Modelsmentioning

confidence: 99%

See 2 more Smart Citations

New Dataset for Forecasting Realized Volatility: Is the Tokyo Stock Exchange Co-Location Dataset Helpful for Expansion of the Heterogeneous Autoregressive Model in the Japanese Stock Market?

Higashide

Tanaka

Kinkyo

et al. 2021

JRFM

View full text Add to dashboard Cite

This study analyzes the importance of the Tokyo Stock Exchange Co-Location dataset (TSE Co-Location dataset) to forecast the realized volatility (RV) of Tokyo stock price index futures. The heterogeneous autoregressive (HAR) model is a popular linear regression model used to forecast RV. This study expands the HAR model using the TSE Co-Location dataset, stock full-board dataset and market volume dataset based on the random forest method, which is a popular machine learning algorithm and a nonlinear model. The TSE Co-Location dataset is a new dataset. This is the only information that shows the transaction status of high-frequency traders. In contrast, the stock full-board dataset shows the status of buying and selling dominance. The market volume dataset is used as a proxy for liquidity and is recognized as important information in finance. To the best of our knowledge, this study is the first to use the TSE co-location dataset. The experimental results show that our model yields a higher forecast out-of-sample accuracy of RV than the HAR model. Moreover, we find that the TSE Co-Location dataset has become more important in recent years, along with the increasing importance of high-frequency trading.

show abstract

Section: Discussionmentioning

confidence: 99%

Section: Literature Review Of Volatility Forecasting Modelsmentioning

confidence: 99%

Section: Literature Review Of Volatility Forecasting Modelsmentioning

confidence: 99%

See 1 more Smart Citation

New Dataset for Forecasting Realized Volatility: Is the Tokyo Stock Exchange Co-Location Dataset Helpful for Expansion of the Heterogeneous Autoregressive Model in the Japanese Stock Market?

Higashide

Tanaka

Kinkyo

et al. 2021

JRFM

View full text Add to dashboard Cite

show abstract

“…This includes beta, inflation rates, trading volume, and volatilities, among others. Recent scholarly publications that apply the approaches that the memochange package implements are, for example, Sibbertsen, Wegener, & Basse (2014), Baillie, Calonaci, Cho, & Rho (2019), and Wenger & Leschinski (2019).…”

Section: Discussionmentioning

confidence: 99%

memochange: An R package for estimation procedures and tests for persistent time series

Wenger¹,

Becker²

2019

JOSS

View full text Add to dashboard Cite

For modeling and forecasting time series it is essential to know whether the series are stationary or non-stationary since many commonly applied statistical methods (such as OLS) are invalid under non-stationarity. Two features that cause a time series to be non-stationary are considered here. On the one hand a time series can be subject to a change in mean, i.e. the expected value of the series changes over time. On the other hand a time series can be subject to a break in the autocovariance often referred to as a change in persistence, i.e. the dependence structure of the series changes over time. Potential examples for both a change in mean and a change in persistence can be found in Figure 1. Figure 1: Left: log squared returns of the NASDAQ index between 2006 and 2009, right: crude oil price over time.The left plot presents the daily log squared returns of the NASDAQ index between 2006 and 2009. It can be seen that in the second part of the series the mean of the log squared return seems to be larger than in the first part of the series. This is evidence for a change in mean, which is likely to be caused by the financial crisis started in August 2007. The right plot shows the monthly price of crude oil between 1986 and 2019. It can be seen that the series is more variable in the second part from year 2000 onwards. This might be caused by a change in the autocovariance structure (i.e. a change in persistence) of the series.The memochange package is an R (R Core Team, 2019) package that identifies such changes in mean and persistence. This helps to avoid model misspecification and improves forecasts of the time series.

show abstract

“…As shown by Adenstedt (1974), this type of behavior implies long-lasting autocorrelations, that is they exhibit long-range dependence. In finance, long-range dependence has been estimated in volatility measures, inflation, and energy prices; see, for instance, Baillie et al (2019), Vera-Valdés (2021b), Hassler and Meller (2014), and Ergemen et al (2016) In the time series literature, the fractional difference operator has become one of the most popular methods to model long-range dependence. Notwithstanding its popularity, Granger argued that processes generated by the fractional difference operator fall into the area of "empty boxes", about theory-either economic or econometric-on topics that do not arise in the actual economy (Granger 1999).…”

Section: Introductionmentioning

confidence: 99%

Nonfractional Long-Range Dependence: Long Memory, Antipersistence, and Aggregation

Vera-Valdés

2021

Econometrics

View full text Add to dashboard Cite

This paper used cross-sectional aggregation as the inspiration for a model with long-range dependence that arises in actual data. One of the advantages of our model is that it is less brittle than fractionally integrated processes. In particular, we showed that the antipersistent phenomenon is not present for the cross-sectionally aggregated process. We proved that this has implications for estimators of long-range dependence in the frequency domain, which will be misspecified for nonfractional long-range-dependent processes with negative degrees of persistence. As an application, we showed how we can approximate a fractionally differenced process using theoretically-motivated cross-sectional aggregated long-range-dependent processes. An example with temperature data showed that our framework provides a better fit to the data than the fractional difference operator.

show abstract

Long Memory, Realized Volatility and Heterogeneous Autoregressive Models

Cited by 32 publications

References 65 publications

New Dataset for Forecasting Realized Volatility: Is the Tokyo Stock Exchange Co-Location Dataset Helpful for Expansion of the Heterogeneous Autoregressive Model in the Japanese Stock Market?

New Dataset for Forecasting Realized Volatility: Is the Tokyo Stock Exchange Co-Location Dataset Helpful for Expansion of the Heterogeneous Autoregressive Model in the Japanese Stock Market?

memochange: An R package for estimation procedures and tests for persistent time series

Nonfractional Long-Range Dependence: Long Memory, Antipersistence, and Aggregation

Contact Info

Product

Resources

About