Since it has become necessary for each individual to be statistically literate, statistical education research has taken teachers' competencies into its agenda. The knowledge needed to teach statistics differs from the knowledge needed to teach mathematics since statistics is different from mathematics. Teachers and researchers need to consider these differences and be aware of the challenges of statistics teaching. This article focuses on the nature of statistical knowledge for teaching (SKT). Models of conceptualizing and measuring SKT from research literature were reviewed critically. The strengths and weaknesses of models were discussed. The article concludes with some implications for teacher education and research.