Copyright (c) 2025 Synergía
This work is licensed under a Creative Commons Attribution-NonCommercial-ShareAlike 4.0 International License.
In university-level statistics education, particularly in the topic of hypothesis testing, many students face difficulties in understanding abstract concepts such as the p-value, Type I and Type II errors, or the impact of sample size. In response to this challenge, this research proposes a didactic alternative based on the use of technological tools such as Google Colab, Python, and generative artificial intelligence models like ChatGPT to perform simulations that bridge theory and practice. Using a real case as a starting point, six simulations were conducted with different statistical parameters. This made it possible to concretely and visually observe how statistical decisions change when modifying variables such as the observed mean, standard deviation, significance level, and sample size. The results highlight not only the pedagogical value of simulations but also their ability to foster understanding, discussion, and reflection. Beyond calculations, students can visualize how sampling distributions behave and make decisions based on this, transforming the learning experience into something more participatory and meaningful. Additionally, the digital environment offers immediate feedback and opportunities to explore different scenarios, fostering real-time analytical skills. This approach does not seek to replace theory but rather to complement it with resources that make statistical thinking more accessible. In conclusion, computational simulation and artificial intelligence are valuable allies in rethinking how statistics is taught, enhancing both students’ understanding and interest.
