hcp_garch: Change Finder using GARCH

In harbinger: A Unified Time Series Event Detection Framework

Change Finder using GARCH

Description

Change-point detection for variance shifts using a GARCH-based residual model. The detector flags change points when the observed series departs from the expected volatility pattern estimated by the fitted GARCH model. Wraps the GARCH model presented in the rugarch package.

Usage

hcp_garch(sw_size = 5)

Arguments

sw_size

Sliding window size

Value

hcp_garch object

References

• Ogasawara, E., Salles, R., Porto, F., Pacitti, E. Event Detection in Time Series. 1st ed. Cham: Springer Nature Switzerland, 2025. doi:10.1007/978-3-031-75941-3

Examples

library(daltoolbox)

# Load change-point example data
data(examples_changepoints)

# Use a volatility example
dataset <- examples_changepoints$volatility
head(dataset)

# Configure ChangeFinder-GARCH detector
model <- hcp_garch()

# Fit the model
model <- fit(model, dataset$serie)

# Run detection
detection <- detect(model, dataset$serie)

# Show detected change points
print(detection[(detection$event),])

harbinger documentation built on May 14, 2026, 5:06 p.m.