做面板回归，特别是xtabond2，通常会报告如下过度识别结果：
Sargan test of overid. restrictions: chi2(59)   =  61.74  Prob > chi2 =  0.378
  (Not robust, but not weakened by many instruments.)
Hansen test of overid. restrictions: chi2(59)   =  28.13  Prob > chi2 =  1.000
  (Robust, but can be weakened by many instruments.)

意为：Sargan虽不稳健，但不会受到过多工具变量的影响。Hansen虽然稳健，但会受到过多工具变量的影响。


我看另一个教程（by Elitza Mileva），有这么一句话：
when the number of instruments is greater than the number of countries the Sargan test may be weak.
到底哪个受工具变量个数的影响大些呢？