The point of statPREP is to help you become comfortable and proficient teaching introductory statistics with a pedagogy that’s based on working with data.

One reason to work with data is that it’s good practice. For instance, the American Statistical Associations “Guidelines for Assessment and Instruction in Statistics Education (GAISE)” lists teaching with data as one of it’s primary recommendations.

Recommendation 3: Integrate real data with a context and a purpose

Using real data in context is crucial in teaching and learning statistics, both to give students experience with analyzing genuine data and to illustrate the usefulness and fascination of our discipline. Statistics can be thought of as the science of learning from data, so the context of the data becomes an integral part of the problem-solving experience. — GAISE College Report (2016) p. 17

There are other important reasons to base the pedagogy of teaching statistics in working with data. For one, your students are encountering ever more sophisticated displays of data. They will be better consumers of such displays if they have seen how they can be created.

Working with data can make statistical concepts more concrete and easy to comprehend. The tradition in statistics education has been to use algebra as a way to express statistical ideas. For the large majority of students, the algebra obscures as much as it illuminates.

Statistics has always fit uncomfortably into the culture of mathematics. Mathematics is strongly rooted in deductive reasoning and proof, while statistics is about *inductive* reasoning: claims, not proof. It’s also the case that important contemporary applications of statistics are very much embedded in a cycle of hypothesis generation, challenge, and revision. This cycle is draws very strongly on expertise in the field of application. And statistical results are only useful if they can be successfully communicated to the people who need to know.

The traditions of mathematics have encouraged statistics to be seen as a branch of probability. Perhaps surprisingly, formal probability is not at all central to statistics.^{1} Historically, the connection between probability and statistics emerges mainly as the way to represent variation using algebraic symbols.

Of course, faculty trained in mathematics are extra-ordinarily good at algebra. So it’s natural that they are receptive to presenting statistics using algebraic notation and focusing on ideas involving provable statements (such as the central limit theorem or the t-distribution), even though those ideas provide only a rough approximation to real-world processes. Working with data can help ground learning statistics in the viscissitudes, uncertainties, and subjectivity of using data to gain insight.

We believe that instructors ought to be tightly connected to the ways their subjects can be used in applications. Ideally, and according to guidelines^{2} issued by the Mathematical Association of America and the American Statistical Association, statistics instructors should be fully qualified as professionals in working with data.

It might seem obvious that teaching statistics and working with data go hand in hand and that statistics instructors ought to be data experts. But until recently, learning to work with data was an informal and often stressful chore of “picking it up.” Now, with the growing realization of the importance of using data to inform and guide decisions, much inventiveness and insight has gone into to developing software tools that are powerful, flexible, and accessible to non-programmers. In this statPREP workshop we’re going to introduce you to those software tools. Then, we’ll work with you to develop lessons for your intro stats course that will be compelling and informative to your students and will display to them that working with data can be both fun and rewarding. We hope you’ll be emboldened not just to teach with data, but to work with data to address questions of particular relevance to you, your students, and your community.

Here’s what GAISE has to say about probability theory: “The original GAISE report recommended less emphasis on probability in the introductory course and we continue to endorse that recommendation. For many students, an introductory course may be the only statistics course that they take; therefore some instructors will want to teach basic probability and rules about random variables, with perhaps the binomial as a special case. However, the GAISE goals and recommendations can be met without these topics.”↩

“Qualifications for teaching an introductory statistics course” ASA/MAA Joint Committee on Undergraduate Statistics link to document↩