This paper examines the role of assessment in research studies focused on the teaching and learning of statistics at the undergraduate or graduate level. Some advantages and limitations for types of assessment methods typically used in statistics education research are summarized. An alternative framework is offered for conceptualizing assessment and its role in studies of statistics education. This framework is based on the theory of conceptual change. An illustration will be offered: a study of the impact of the use of computer simulations on learning statistical inference. Examples of the types of assessment embedded in this ongoing research project will be shared.