Revisiting the Great Ratios Hypothesis*
针对Kaldor提出的恒定比率（大比率）假说，现有实证证据不足的问题，提出一种新的系统混合均值组估计量，能处理非协整、双向因果和跨国误差依赖，基于17国150年数据发现七个比率中有五个得到支持。
Kaldor called the constancy of certain ratios stylized facts, Klein and Kosobud called them great ratios. While they often appear in theoretical models, the empirical literature finds little evidence for them, perhaps because the procedures used cannot deal with lack of co‐integration, two‐way causality, and cross‐country error dependence. We propose a new system pooled mean group estimator that can deal with these features. Monte Carlo results show it performs well compared with other estimators, and using it on a dataset over 150 years and 17 countries, we find support for five of the seven ratios considered.