A CUSUMSQ test for structural breaks in error variance for a long memory heterogeneous autoregressive model

Abstract

For testing error variance instability, a test based on CUSUM squares of the residuals in HAR model is constructed and its limiting null distribution is derived to be a simple function of the standard Brownian bridge. A finite sample Monte-Carlo experiment shows reasonable size and power performances of the proposed test. The test is applied to the log-return realized volatilities of some stock price index and exchange rate to find evidence for variance instability after adjusting long-memories.