Testing on Cointegrating Vectors CAES Working Paper Series A Signal-to-Noise Ratio for Hypothesis Testing on Cointegrating Vectors

This note investigates impacts of a signal-to-noise ratio on \u85nite-sample inference for cointegrating vectors. The ratio is de\u85ned as a measure of the magnitude of a permanent shock relative to a transitory shock. Monte Carlo experiments show that a high signal-to-noise ratio tends to reduce size distortions of a likelihood-based test for a hypothesis on cointegrating vectors. JEL Classi\u85cation Codes: C32, C52, C63