The American College of Rheumatology (ACR) 20% preliminary definition of improvement in rheumatoid arthritis (RA) (ACR20) is widely used in clinical trials to assess response to treatment. The objectives of this analysis were to develop an exposure-response model of ACR20 in subjects receiving treatment with certolizumab pegol and to predict clinical outcomes following various treatment schedules. At each visit, subjects were classified as being ACR20 responders or ACR20 nonresponders or as having dropped out. A Markov mixed-effects model was developed to investigate the effects of the drug on the transitions between the three defined states. Increasing certolizumab pegol exposure predicted an increasing probability of becoming a responder and remaining a responder, as well as a reduced probability of dropping out of treatment. Data from simulations of the ACR20 response rate support the use of dosing regimens of 400 mg at weeks 0, 2, and 4 followed by 200 mg every 2 weeks, or an alternative maintenance regimen of 400 mg every 4 weeks.