Multivariate Behavioral Research, 46:58–89, 2011 Copyright © Taylor & Francis Group, LLC ISSN: 0027-3171 print/1532-7906 online DOI: 10.1080/00273171.2011.544227 Robust Mokken Scale Analysis by Means of the Forward Search Algorithm for Outlier Detection Wobbe P. Zijlstra, L. Andries van der Ark, and Klaas Sijtsma Tilburg University Exploratory Mokken scale analysis (MSA) is a popular method for identifying scales from larger sets of items. As with any statistical method, in MSA the presence of outliers in the data may result in biased results and wrong conclusions. The forward search algorithm is a robust diagnostic method for outlier detection, which we adapt here to identify outliers in MSA. This adaptation involves choices with respect to the algorithm’s objective function, selection of items from samples without outliers, and scalability criteria to be used in the forward search algorithm. The application of the adapted forward search algorithm for MSA is demonstrated using real data. Recommendations are given for its use in practical scale analysis. Exploratory Mokken scale analysis (MSA; Mokken, 1971; Sijtsma & Molenaar, 2002) is a popular method for identifying scales from a larger set of items. Recent examples of MSA are found in criminology (e.g., Santtila et al., 2008), health sciences and medicine (e.g., Watson, Deary, & Shipley, 2008), marketing (e.g., Paas & Sijtsma, 2008), political science (e.g., Jacoby, 2008), psychiatry (e.g., Bech, Wilson, Wessel, Lunde, & Fava, 2009; Korner et al., 2007), psychology (e.g., Watson, Roberts, Gow, & Deary, 2008), and sociology (e.g., Loner, 2008). MSA analyzes discrete item scores that often equal 0 and 1 for incorrect and correct answers, respectively, or 0, 1, 2, 3, 4 for the degree of endorsement to the statements included in rating scale items. MSA may be hampered by the Correspondence concerning this article should be address to Wobbe P. Zijlstra, Department of Methodology and Statistics, Faculty of Social and Behavioral Sciences, Tilburg University, P.O. Box 90153, 5000 LE Tilburg, The Netherlands. E-mail: w.p.zijlstra@uvt.nl 58