Abstract
We show that a popular multiplicative decomposition of volatility has an interpretation as a GARCH model augmented by a time-varying intercept. We parameterize the intercept by a logistic transition function with rescaled time as the transition variable, which provides a flexible and simple way of capturing deterministic non-linear changes in the conditional and unconditional variances.
It is common for financial time series to exhibit these types of shifts. The time-varying intercept makes the model globally nonstationary but locally stationary. We use the theory of locally stationary processes to derive the asymptotic properties of the quasi maximum likelihood estimator (QMLE) of the parameters of the model. We show that the QMLE is consistent and asymptotically normally distributed. To corroborate the results of the analysis, we provide a small simulation study. An empirical application on Oracle Corporation returns demonstrates the usefulness of the model. We find that the persistence implied by the workhorse GARCH(1,1) parameter estimates is reduced by incorporating a time-varying intercept.
It is common for financial time series to exhibit these types of shifts. The time-varying intercept makes the model globally nonstationary but locally stationary. We use the theory of locally stationary processes to derive the asymptotic properties of the quasi maximum likelihood estimator (QMLE) of the parameters of the model. We show that the QMLE is consistent and asymptotically normally distributed. To corroborate the results of the analysis, we provide a small simulation study. An empirical application on Oracle Corporation returns demonstrates the usefulness of the model. We find that the persistence implied by the workhorse GARCH(1,1) parameter estimates is reduced by incorporating a time-varying intercept.
| Original language | English |
|---|---|
| Title of host publication | NORDSTAT 2023 Booklet with Abstracts |
| Number of pages | 1 |
| Place of Publication | Gothenburg |
| Publication date | 17.06.2023 |
| Pages | 24 |
| Publication status | Published - 17.06.2023 |
| MoE publication type | B3 Article in conference proceedings |
| Event | 29th Nordic Conference in Mathematical Statistics, NORDSTAT 2023 - Department of Mathematical Sciences at Chalmers University of Technology, Gothenburg, Sweden Duration: 19.06.2023 → 22.06.2023 Conference number: 29 https://nordstat2023.org/ |
Keywords
- 112 Statistics and probability
- Conditional heteroskedasticity
- Locally stationary GARCH
- Nonlinear time series
- Quasi maximum likelihood
- Time-varying GARCH
- Smooth transition
Areas of Strength and Areas of High Potential (AoS and AoHP)
- AoS: Financial management, accounting, and governance