Hello everyone,

I have the following question related to testing residuals for serial correlation after using the Common Correlated Effects estimator of Pesaran (2006).
In particular, suppose we estimate using the pooled version of the estimator - what would be the appropriate procedure for testing for serial correlation?
In a paper by Eberhardt et al. (Review of Economics and Statistics, 2013) the authors use the Arellano and Bond (1991) test (using the abar command). However, Millo (Journal of Applied Econometrics. 2018) in his replication of the paper argues for using the approach outlined in Wooldridge (2010)

Any ideas?