Introductory Statistics Courses

Guidelines for Introductory Statistics Courses

Introductory statistics courses serve as students’ first formal encounter with statistical thinking and methodology. These courses should emphasize the statistical process while building conceptual understanding that prepares students for advanced study or informed citizenship.

Student Learning Outcomes for Introductory Statistics

What are Student Learning Outcomes?

Student learning outcomes (SLOs) describe the knowledge, skills, and abilities students should acquire over a given time period. Aside from articulating the specific academic goals for students, they also indicate how students will demonstrate evidence of their learning; that is, SLOs need to be measurable.

Student learning outcomes have different levels of granularity. A program may provide SLOs at the program level, while individual instructors may provide SLOs for their course or even for each individual class meeting. The learning outcomes provided here are at the course level; that is, the SLOs articulate what students should know and be able to do after completing an introductory statistics course.

Our goal was to present a set of SLOs that describe important outcomes for students completing an introductory statistics class. While instructors could use them verbatim, they could also be adapted to meet the specific needs of their students. We expect that most instructors will add, modify, or substitute these SLOs to suit their course.

Why are Course Student Learning Outcomes Important?

SLOs serve multiple purposes. First, they can provide students with a roadmap for what they can expect to know and do after finishing their introductory statistics course. Second, SLOs can help statistics instructors prioritize content, create appropriate assessments, and design instructional materials for their course.

Metaphorically, the SLOs identify the learning destination for the road trip of introductory statistics. The route and itinerary of the course can be mapped out to help students incrementally develop the knowledge, skills, and abilities addressed in the SLOs so that the journey is successful. As such, the use of SLOs can evoke critical, evidence-based thought about student learning.

Student Learning Outcomes vs. The College GAISE Recommendations

The SLOs for introductory statistics provided here serve a very different purpose than the College GAISE Recommendations provided elsewhere in this document. The SLOs for introductory statistics provided here are focused on the outcomes and goals for students’ learning (i.e., student-facing), whereas the College GAISE Recommendations are designed to aid instructors and other stakeholders in understanding current best practices in the teaching of statistics and data science (instructor-facing). To continue our road trip metaphor, the College GAISE Recommendations are a general guidebook for road trips. They offer instructional insight and guidance for the trip that is useful for all road trips regardless of the learning destination or route taken.

After completing an Introductory Statistics course, students should be able to:

  1. Identify cases, variables, and types of variables in data sets, including multivariable data sets.

  2. Explain how study design affects what conclusions can be drawn from the data. In particular, explain the importance of random sampling and random assignment.

  3. Identify and interpret appropriate graphs and summary statistics in both univariate and multivariate settings.

  4. Use statistical software or apps to create visualizations, produce summary statistics, and carry out the computational aspects of statistical analysis.

  5. Articulate the role that random variation plays in statistical inference. In particular, articulate its role in generalizing from a sample to a population.

  6. Identify the key methods to use in statistical inference and interpret results from those methods.

  7. Recognize that sampling variation is one reason that conclusions drawn from statistical inference might be incorrect, and that replication and reproducibility are important to verify conclusions.

  8. Use statistical models, such as linear regression, for prediction.

  9. Recognize ethical issues and dilemmas in statistical practice.

  1. Communicate, clearly and in context, results obtained from data.