Combating anti-statistical thinking using simulation-based methods throughout the undergraduate curriculum

The use of simulation-based methods for introducing inference is growing in popularity for the Stat 101 course, due in part to increasing evidence of the methods ability to improve students’ statistical thinking. This impact comes from simulation-based methods (a) clearly presenting the overarching logic of inference, (b) strengthening ties between statistics and probability or mathematical concepts, (c) encouraging a focus on the entire research process, (d) facilitating student thinking about advanced statistical concepts, (e) allowing more time to explore, do, and talk about real research and messy data, and (f) acting as a firmer foundation on which to build statistical intuition. Thus, we argue that simulation-based inference should be an entry point to an undergraduate statistics program for all students, and that simulation-based inference should be used throughout all undergraduate statistics courses. In order to achieve this goal and fully recognize the benefits of simulation-based inference on the undergraduate statistics program we will need to break free of historical forces tying undergraduate statistics curricula to mathematics, consider radical and innovative new pedagogical approaches in our courses, fully implement assessment-driven content innovations, and embrace computation throughout the curriculum.

💡 Research Summary

The paper argues that the pervasive problem of “anti‑statistical thinking” – the tendency of students to treat statistics as a set of mechanical calculations divorced from real data and reasoning – can be effectively addressed by making simulation‑based inference (SBI) the cornerstone of undergraduate statistics education. The authors begin by diagnosing the historical entanglement of statistics curricula with mathematics, noting that traditional courses emphasize formulaic derivations, closed‑form solutions, and abstract probability theory at the expense of intuitive understanding and authentic data work. They cite a growing body of empirical studies from introductory “Stat 101” courses that demonstrate how SBI, when introduced early, improves students’ conceptual grasp of inference, increases engagement, and fosters a more accurate mental model of statistical reasoning.

Six core benefits of SBI are identified. First, SBI makes the logical structure of hypothesis testing transparent: by repeatedly generating random samples and computing test statistics, students see directly how the null distribution arises and why p‑values measure extremeness relative to that distribution. Second, it tightens the conceptual bridge between probability and inference, because learners experience probability as a generative process rather than an abstract set of axioms. Third, SBI encourages a holistic view of the research cycle, integrating problem formulation, data collection, cleaning, visualization, modeling, and interpretation into a single workflow rather than treating inference as an isolated step. Fourth, it provides a natural scaffold for advanced concepts such as bootstrapping, permutation tests, and Bayesian posterior simulation, allowing these topics to be introduced earlier and with greater intuition. Fifth, the approach frees classroom time for authentic, “messy” data sets, giving students practice with missing values, outliers, and real‑world data structures that are rarely encountered in textbook examples. Sixth, repeated simulation cultivates statistical intuition; learners develop a feel for variability, sampling error, and the stochastic nature of data without relying solely on algebraic manipulation.

To translate these benefits into a curriculum that spans the entire undergraduate program, the authors propose four systemic changes. 1) Decouple statistics education from a purely mathematical framework and re‑orient it around data‑driven problem solving. 2) Adopt radical, student‑centered pedagogies such as flipped classrooms, project‑based learning, and collaborative inquiry, where students design, run, and interpret their own simulations. 3) Implement assessment‑driven content redesign: replace traditional closed‑book, formula‑recall exams with performance‑based tasks that evaluate simulation design, result interpretation, and communication of findings. 4) Institutionalize computation across all courses, ensuring that every student gains fluency in a statistical programming language (R, Python, or web‑based tools) and can execute simulations autonomously.

The paper concludes that embedding SBI at the entry point and sustaining it throughout the curriculum will shift the educational paradigm from “statistical calculation” to “statistical thinking.” This shift promises to produce graduates—whether they major in statistics or not—who are equipped to make evidence‑based decisions, critically evaluate research, and engage with the data‑rich world. The authors also outline future research directions, including longitudinal studies of learning outcomes, professional development programs for faculty, and cross‑disciplinary collaborations that embed SBI in non‑statistical majors. By embracing these reforms, the discipline can overcome its historical inertia and fulfill its mission as a central pillar of quantitative literacy in higher education.