The purpose of this article is to sketch a hypothetical descriptive framework of statis-tical knowledge for teaching. Because statistics is a discipline in its own right rather than a branch of mathematics, the knowledge needed to teach statistics is likely to differ from the knowledge needed to teach mathematics. Doing statistics involves many primarily nonmathematical activities, such as building meaning for data by examining the context and choosing appropriate study designs to answer questions of interest. Although there are differences between mathematics and statistics, the two disciplines do share common ground in that statistics utilizes mathematics. This connection suggests that existing research on mathematical knowledge for teaching can help inform research on statistical knowledge for teaching. I propose the use of research from the Learning Mathematics for Teaching (LMT) project to help shape the discussion. I conclude by identifying areas of needed research and suggesting directions for teacher education efforts in statistics.
Randall E. Groth, 147 Caruthers Hall, Seidel School of Education and Professional Studies, Salisbury University, Salisbury, MD 21801; firstname.lastname@example.org