Extent of type I and type II errors in editorial decisions: A case study on Angewandte Chemie International Edition

Selection processes are never faultless. We investigate the predictive validity of the manuscript selection process at Angewandte Chemie International Edition (AC-IE), one of the prime chemistry journals worldwide, and conducted a citation analysis for manuscripts that were accepted by the journal or rejected but published elsewhere (n = 1817). With the bibliometric data, we were able to calculate the extent of type I and type II errors of the selection decisions. We found that the decisions regarding 15% of the manuscripts show a type I error (accepted manuscripts that did not perform as well as or worse than the average rejected manuscript). Moreover, the decisions regarding 15% of the manuscripts are affected by a type II error (rejected manuscripts that performed equal to or above the average accepted manuscript). (C) 2009 Elsevier Ltd. All rights reserved.