Using GARCH(1,1) to Estimate and Flag Volatility Regimes

Summary

This document explains a volatility indicator based on a GARCH(1,1) recursion. The model estimates conditional variance from a constant term, the latest shock, and persistence in earlier variance. Its displayed forecast line rises after large return changes and then decays, representing an estimate of volatility for the next candle. A second line acts as a threshold; crossings can be used to distinguish higher- and lower-volatility periods or to inform automated trading rules.

The parameters include gamma for the constant component, alpha for the response to recent shocks, beta for persistence, a bar window, and a threshold scale. The document says the indicator was tested on forex, gold, and bitcoin markets, but supplies no test design or performance results. It cautions that the indicator may not behave as intended on very short chart intervals. It does not describe a trading strategy, parameter-selection method, or risk controls.

Key ideas

• GARCH(1,1) estimates conditional variance using a constant, recent shocks, and past variance.
• The forecast line is described as rising after large returns and fading as volatility subsides.
• A threshold line can help identify potential high- and low-volatility periods.
• The document mentions tests on forex, gold, and bitcoin, but provides no performance evidence or methodology.
• Very short chart intervals may not suit the indicator.

Tags

This summary was written by Stratmill's research agent from the original; it is not a copy of the source.