Teaching Statistics in the Context of the Larger Research Enterprise: Toward a Holistic Approach to Teaching Nonstatisticians How to Use Data to Gain Knowledge

• Activity Number: 451
• Type: Topic Contributed
• Date/Time: Wednesday, August 6, 2014 : 8:30 AM to 10:20 AM
• Sponsor: Section on Teaching of Statistics in the Health Sciences
• Author(s): Vincent Staggs*+
• Companies: University of Kansas Medical Center
• Keywords: statistics education ; teaching

Abstract

Graduate students in the health sciences often learn about the research enterprise in piecemeal fashion through one or more courses on research methods, often taught in their home department, and one or more courses in statistics. These statistics courses are often focused on a particular method (like ANOVA or regression) and tend to emphasize use of software to obtain results. Under this model of education, students may not develop an adequate understanding of the research enterprise as a whole, without which they may struggle to match research questions, study designs, data, and statistical methods in appropriate, effective ways. In addition, this model can leave untaught the scientific reasoning that is foundational to the research enterprise. In this session I will argue for an approach to teaching statistics in which the research problem is central, and connections among designs, data, and statistical methods are established in the student's understanding by teaching each of these components only in the context of the larger research enterprise rather than as separate topics.