Dopamine (DA) neurons are fundamental to many aspects of behavior, and dysfunction of the DA system contributes to a wide range of disorders, including drug addiction. How does DA contribute to such a diversity of functions and dysfunctions? Part of the answer may relate to recent discoveries that DA neurons respond to a wide range of behavioral variables - not only to reward and reward-predicting cues, as traditionally examined, but also to other variables including position, movement, and behavioral choices. However, to date, the relative contributions of these behavioral variables to DA responses have not been examined quantitatively, in part because cellular resolution DA recordings have not been performed in behavioral settings with sufficient complexity and quantification to examine these diverse variables simultaneously. To address this gap, we propose to perform two-photon imaging from ensembles of midbrain DA neurons and their target neurons as mice learn to perform a complex decision-making task. However, characterizing the relationship between neural activity and behavior in this complex dataset presents a number of statistical challenges. These include the autocorrelation of the calcium indicator, the correlation between behavioral variables, the possibility of changes in the relationship between neural activity and behavior over time, and the need to leverage the availability of simultaneously measured neurons in order to improve statistical efficiency. Thus, we propose a suite of new statistical tools to address all of these challenges. These tools will be broadly applicable to the analysis of datasets throughout the addiction circuits (and the nervous system more broadly).