Each student with her/his own data: understanding sampling distributions

TL;DR

This paper introduces an innovative, interactive web-based method for helping students understand sampling distributions by using personalized datasets, promoting active learning and empirical exploration of estimator variability.

Contribution

It presents a novel approach where students use individual datasets to empirically study sampling distributions, enhancing understanding through active participation and personalized data.

Findings

Improved student understanding of sampling variability

Successful implementation of personalized datasets via a web platform

Enhanced engagement and active learning in statistics education

Abstract

Sampling distribution, a foundational concept in statistics, is difficult to understand, since we usually have only one realization of the estimator of interest. In this work, we present an innovative method for helping university students understand the variability of an estimator. In our approach, each student uses a different data set, getting diverse estimations. Then, sharing the results, we can empirically study the sampling distribution. After some "handmade" experiences, we have built a web page to deliver a personalized data set for each student. Through this web page, we can also reformulate the role of the student in the classroom, inviting him/her to became an active player, submitting the solution to different problems and checking whether they are correct. In this work we present a recent experience in such direction.