The primary efficacy end point was analyzed in a pairwise manner for the 2 apremilast treatment groups compared with placebo, using the continuity-corrected chi-square test. A 95% 2-sided confidence interval for the odds ratio was also presented. As a sensitivity analysis for the ACR20 improvement response, the Cochran-Mantel-Haenszel test, controlled for MTX use, was performed to compare each treatment group with the placebo group.