Authors: Sharon Koon; Akihito Kamata
Addresses: Florida State University, 2010 Levy Avenue, Suite 100, Tallahassee, Florida 32310, USA ' University of Oregon, 102S Lokey Education Building, Eugene, Oregon 97403-5267, USA
Abstract: This study applied the odds-ratio (Penfield, 2008), the multinomial logistic regression (Kato et al., 2009), and the standardised distractor analysis (Schmitt and Bleistein, 1987) methods in the examination of differential distractor functioning (DDF) effects. Using data from the administration of one statewide mathematics assessment, these methods were applied to provide insight into two research questions; 1) whether the magnitude and pattern of the DDF effect is constant across all methods; 2) whether the pattern of DDF effects supports differential item functioning (DIF) findings. While some differences in results were found, all three methods present a viable option for use in improving test items included in statewide assessment programmes.
Keywords: differential item functioning; DIF; differential distractor functioning; DDF; odds ratio; multinomial logistic regression; standardised distractor analysis; mathematics assessment; statewide assessment programmes; USA; United States.
International Journal of Quantitative Research in Education, 2013 Vol.1 No.4, pp.364 - 382
Received: 29 Jan 2013
Accepted: 17 Jun 2013
Published online: 12 Dec 2013 *