Macro?Finance Decoupling: Robust Evaluations of Macro Asset Pricing Models

This paper shows that robust inference under weak identification is important to the evaluation of many influential macro asset pricing models, including (time?varying) rare?disaster risk models and long?run models. Building on recent developments in conditional literature, we provide a novel specification test by simulating critical value sufficient statistic. statistic can be intuitively interpreted as measure capturing macroeconomic information decoupled from underlying content theories. Macro?finance decoupling an effective way improve power when theories are difficult refute because severe imbalance about key model parameters between moment restrictions cross?equation restrictions. We apply proposed time?varying construction uncertainty sets.