xtabond2 command : Fix for the Arellano-Bond Test for Autocorrelation of order 1

[Duarte Gomes]

Is it really mandatory to reject the Null Hypothesis of the Arrelano-Bond AR(1)?

If so, is there a way to reduce the p-value to less than 0.1?
I would appreciate it if there was some literature about this problem because I can´t find anything.


Thank you.

[David Roodman]

In How to Do xtabond2, it says:

That means you should just ignore it. xtabond2 only reports it because it started as a clone of Stata's xtabond, which also reports it.