Welcome to the new version of CaltechAUTHORS. Login is currently restricted to library staff. If you notice any issues, please email coda@library.caltech.edu
Published January 2019 | public
Journal Article

Improved method for detecting acquirer fixed effects


Large merger and acquisition (M&A) samples feature the pervasive presence of repetitive acquirers. They offer an attractive empirical context for revealing the presence of acquirer fixed effects (permanent abnormal performance). But panel data M&A are quite heterogeneous; just a few acquirers undertake many M&As. Does this feature affect statistical inference? To investigate the issue, our study relies on simulations based on real data sets. The results suggest the existence of a bias, confirming suspicions reported in the extant literature about the validity of fixed-effect regression based statistics (R- square, adjusted R- square and fixed effects Fisher tests) used to detect the presence and significance of acquirer fixed effects. We introduce a new resampling method to detect acquirer fixed effects with attractive statistical properties (size and power) for samples of acquirers that complete at least five acquisitions. The proposed method confirms the presence of acquirer fixed effects but only for a marginal fraction of the acquirer population. This result is robust to endogenous attrition and varying time periods between successive transactions.

Additional Information

© 2019 Elsevier B.V. Received 19 September 2017, Revised 3 December 2018, Accepted 27 December 2018, Available online 3 January 2019. We are grateful for the many suggestions provided by participants to the December 2016 Univ. Lille Monday Finance Seminar and to the May 2017 French Finance Conference (Valence - France) and in particular comments by Guosong Xu. We thank Luc Bauwens for the fruitful discussions that we have had during the development of this research project and also the Journal of Empirical Finance editor and anonymous referees who help us to significantly improve our work. All errors remain ours.

Additional details

August 22, 2023
October 19, 2023