The diffusion decision model is a powerful tool for explaining behavior in two-choice discrimination tasks. This article reviews the model and its applications, focusing on how it translates behavioral data into components of cognitive processing. Three experiments are conducted to illustrate the model's predictions for the effects of stimulus difficulty, instructions emphasizing speed or accuracy, and the relative proportions of stimuli on response time (RT) distributions and accuracy. The model's strong constraints ensure its empirical testability and potential falsifiability. The model's broad applications, including research in aging and neurophysiology, are also discussed. The diffusion model separates the quality of evidence, decision criteria, and nondecision processes, and it accounts for the shapes and behaviors of RT distributions. The model's predictions for RT distributions are consistent with empirical data, showing that changes in drift rate lead to larger changes in the tail of the distribution than in the leading edge, while changes in boundary separation affect the leading edge more than the tail. The model's ability to explain the effects of speed versus accuracy instructions and the impact of response proportions on RTs and accuracy is also demonstrated. The article concludes by highlighting the model's success in fitting experimental data and its potential for advancing research in various domains.The diffusion decision model is a powerful tool for explaining behavior in two-choice discrimination tasks. This article reviews the model and its applications, focusing on how it translates behavioral data into components of cognitive processing. Three experiments are conducted to illustrate the model's predictions for the effects of stimulus difficulty, instructions emphasizing speed or accuracy, and the relative proportions of stimuli on response time (RT) distributions and accuracy. The model's strong constraints ensure its empirical testability and potential falsifiability. The model's broad applications, including research in aging and neurophysiology, are also discussed. The diffusion model separates the quality of evidence, decision criteria, and nondecision processes, and it accounts for the shapes and behaviors of RT distributions. The model's predictions for RT distributions are consistent with empirical data, showing that changes in drift rate lead to larger changes in the tail of the distribution than in the leading edge, while changes in boundary separation affect the leading edge more than the tail. The model's ability to explain the effects of speed versus accuracy instructions and the impact of response proportions on RTs and accuracy is also demonstrated. The article concludes by highlighting the model's success in fitting experimental data and its potential for advancing research in various domains.