Resources for Department Chairs

The American Statistical Association and the Mathematical Association of America (MAA) have jointly developed recommended qualifications for an instructor teaching a modern introductory statistics course.

In the joint statement, Qualifications for Teaching an Introductory Statistics Course, the two groups encourage effective teaching in undergraduate statistical education and offer a series of qualifications and resources that will assist nonstatistics departments at universities and colleges with hiring qualified candidates or training existing instructors to acquire the necessary skill set.

The 2015 Committee on the Undergraduate Program in Mathematics (CUPM) Guide to Majors in the Mathematical Sciences states that every student majoring in the mathematical sciences should take an introductory course in applied statistics, with a clear focus on data analysis. We recommend this course be taken during the first two years of the undergraduate program and it focus squarely on applied data analysis. This is a course quite distinct from the usual upper-level sequence in probability and mathematical statistics offered as an elective in most undergraduate mathematics programs and also quite distinct from the low-level procedural course or quantitative literacy course taught at many institutions.

What Do Statistics Courses Look Like?
In 2000, the symposium titled Improving the Work Force of the Future: Opportunities in Undergraduate Statistics Education allowed educators to discuss and make recommendations for the future of undergraduate courses and programs in statistics. “Undergraduate Statistics Education: An Introduction and Review of Selected Literature” (2002) discusses the symposium and the literature that supported it.

There are many ideas, textbooks, and software designed to help students understand statistical thinking. The following papers discuss what good courses in statistics should contain. Although they were published in 1999 and 2002, the basic ideas are still true today.

• Garfield, J., B. Hogg, C. Schau, and D. Whittinghill. 2002. First Courses in Statistical Science: The Status of Education Reform Efforts. Journal of Statistics Education, 10(2).
• Higgins, J. 1999. Nonmathematical Statistics: A New Direction for the Undergraduate Discipline. The American Statistician, 53(1).

The ASA published its 2014 Curriculum Guidelines for Undergraduate Programs in Statistical Science. The guidelines remain true to the previous guidelines, while allowing for an increased emphasis in topics such as Big Data and statistical software.

Statistics Majors
The guidelines state that students need a deep understanding of fundamental concepts and exposure to a variety of topics and methods. The curriculum should provide students with sufficient background in the following areas:

• Statistical methods and theory (e.g., design of studies, statistical modeling, exploratory data analysis, etc.)
• Data manipulation and computation
• Mathematical foundations (e.g., calculus, linear algebra, probability, and their connections with statistics)
• Statistical practice (including strong communication and technical skills)

Statistics Minors or Concentrations
The guidelines also include a section on minors and concentrations. For quantitatively oriented students in fields such as mathematics, biology, business, and behavioral and social sciences, or those planning to teach at the K–12 level, such minors or concentrations may be more feasible than a full statistics major. The core of a statistics minor or concentration should consist of the following:

• General statistical methodology (e.g., statistical thinking, estimation, testing, resampling)
• Statistical modeling (e.g., simple and multiple regression, confounding, diagnostics)
• Facility with professional software and data management skills
• Multiple experiences analyzing data and communicating results

An older article by Ann Cannon, et al. also discusses the statistics minor and offers answers to questions that might arise about a particular curriculum design or revision.

The ASA also endorsed Curriculum Guidelines for Undergraduate Programs in Data Science (2016). The following six main subject areas are mentioned in the guidelines:

• Data description and curation
• Mathematical foundations
• Computational thinking
• Statistical thinking
• Data modeling
• Communications, reproducibility, and ethics

The guidelines also provide an outline for an undergraduate major in data science.

It may be useful for candidates under review and department chairs to consider portions of the 2000 MAA Guidelines for Programs and Departments in Undergraduate Mathematical Sciences, especially the ASA’s endorsement of these guidelines. Below are some key points made in this endorsement:

• Ideally, mathematical sciences departments in which statistics courses are taught should hire faculty with graduate degrees in statistics.
• Once a mathematical sciences department has successfully hired statistics faculty, it should provide sufficient resources and mentoring to enable them to succeed in their teaching and professional development. While travel funds are important for all new faculty members, they can be especially important for statisticians who are housed in a department of nonstatisticians. These faculty members have a particular need for travel to conferences and workshops to meet with collaborators and gain new ideas about the teaching of statistics.
• Mathematical sciences departments should also recognize the value of statistical consulting as a legitimate and important form of scholarship and professional development.
• If a statistician is expected to provide consulting services to colleagues and students throughout the institution … then the institution should make reassigned/released time available for that purpose.
• If the department has only one or two statistics faculty members, it should seek outside persons to serve as advisers for the department and mentors for these isolated faculty members early in their careers.
• When a department with only one statistician is evaluating the person’s teaching, the department should seek input from statisticians at nearby institutions or from the ASA. Since the teaching of statistics differs from that of mathematics in several ways, this input can help the department assess whether the statistician’s teaching is consistent with expectations and recommendations in the field.
• The ASA strongly supports the position that mathematics and statistics are separate disciplines and that statistics courses should be taught by those trained in the subject. “In cases where a department offers a course or courses in a particular discipline, but does not have a faculty member with expertise in that discipline, the department should take special care to consult the curricular guidelines of the relevant professional society in that discipline.” (MAA guidelines section D.1.g)

We encourage mathematics departments not to be overly prescriptive in stating what is adequate in terms of professional involvement for a statistician. While statisticians should be able to provide evidence that they are working in their field(s) as engaged scholars, this work may look different than research in mathematics. It is important to recognize that the interdisciplinary nature of statistics encourages a wide range of scholarly activities. For example, scholarly engagement may emphasize integration, organization, and synthesis such as the creation of software, consulting within multiple disciplines, publishing in journals outside of their field, leading workshops, presenting at conferences, or pursuing research grants. It is best to provide clear expectations for scholarship in writing to any statistician who is hired within a mathematics or mathematical sciences department. Below is a limited set of perspectives on hiring statisticians:

• Hiring a Statistician at a Liberal Arts College
• Kuiper, S., J. Legler, and C. Morgan. 2005. Choosing a Career as a Statistician in a Liberal Arts College. Amstat News, 339:22–24.