“…In addition, even when items are pretested, because DIF could be a manifestation of an interaction between different factors distinguishing groups (Penfield & Camilli, 2007), DIF could still arise in the assessment. Indeed, data analysis of international large-scale assessments such as the Programme for International Student Assessment (PISA), which we illustrate in this study, provides empirical evidence of DIF across national versions of the same test (Asil & Brown, 2016;Ercikan & Koh, 2005;Grisay, de Jong, Gebhardt, Berezner, & Halleux-Monseur, 2007;Grisay, Gonzalez, & Monseur, 2009;Hauger & Sireci, 2008;Huang, Wilson, & Wang, 2016;Kreiner & Christensen, 2014;Le, 2009;Oliveri, Olson, Ercikan, & Zumbo, 2012;Sandilands, Oliveri, Zumbo, & Ercikan, 2013;Wu & Ercikan, 2006;Xie & Wilson, 2008). It is then common to resort to statistical methods for the post hoc accounting of DIF.…”