A brief review of various information criteria is presented for the detection of differential item functioning (DIF) under item response theory (IRT). An illustration of using information criteria for model selection as well as results with simulated data are presented and contrasted with the IRT likelihood ratio (LR) DIF detection method. Use of information criteria for general IRT model selection is discussed.
Keywords: Akaike information criterion; Bayesian information criterion; differential item functioning; information criteria; item response theory; likelihood ratio test; marginal maximum likelihood estimation.