Abstract
In this study, a new item response theory model is developed to account for the situation where respondents overreport or underreport their actual opinion corresponding to the positive or negative direction of an issue measured in a self-report assessment. Such behavior is conceptualized as a mechanism that not only deceives but transfers selections. In the proposed model, such mechanism is performed by incorporating a deception term into a multidimensional rating scale (MRS) model and then multiplying by a transfer term, which is performed by an indicator function and a transition matrix separately. The proposed model is presented in a Bayesian framework approximated by Markov Chain Monte Carlo (MCMC) algorithms. Through a series of simulations, the parameters under the proposed model are recovered well. The methodology is also implemented within an online experimental study to demonstrate its application.