The consideration of a patient's treatment preference may be essential in determining how a patient will respond to a particular treatment. While traditional clinical trials are unable to capture these effects, the two-stage randomized preference design provides an important tool for researchers seeking to understand the role of patient preferences. In addition to the treatment effect, these designs seek to estimate the role of preferences through testing of selection and preference effects. The R package preference facilitates the use of two-stage clinical trials by providing the necessary tools to design and analyze these studies. To aid in the design, functions are provided to estimate the required sample size and to estimate the study power when a sample size is fixed. In addition, analysis functions are provided to determine the significance of each effect using either raw data or summary statistics. The package is able to incorporate either an unstratified or stratified preference design. The functionality of the package is demonstrated using data from a study evaluating two management methods in women found to have an atypical Pap smear.