An asymptotically F-distributed Chow test in the presence of heteroscedasticity and autocorrelation

This study proposes a simple, trustworthy Chow test in the presence of heteroscedasticity and autocorrelation. The is based on series autocorrelation robust variance estimator with judiciously crafted basis functions. Like classical normal linear regression, proposed employs standard F distribution as reference distribution, which justified under fixed-smoothing asymptotics. Monte Carlo simulations show that null rejection probability asymptotic closer to nominal level than chi-square test.