Accessible Conceptions of Statistical Inference: Pulling Ourselves Up by the Bootstraps

Abstract

With the rapid, ongoing expansions in the world of data, we need to devise ways of getting more students much further, much faster. One of the choke points affecting both accessibility to a broad spectrum of students and faster progress is classical statistical inference based on normal theory. In this paper, bootstrap-based confidence intervals and randomisation tests conveyed through dynamic visualisation are developed as a means of reducing cognitive demands and increasing the speed with which application areas can be opened up. We also discuss conceptual pathways and the design of software developed to enable this approach.

A conceptual-empirical typology of social science research methods pedagogy

“…These approaches were designed to make difficult content accessible (see Nind and Lewthwaite 2018b). In this vein, strategies included chunking material, complexity reduction strategies such as bootstrapping (a statistical operation also used as a pedagogic imperative (Wild et al 2017)), removing obstacles, stream-lined software, translating terms, backfilling with technical skill and scaffolding concepts.…”

Bringing Visual Inference to the Classroom

“…These distributions are very abstract ideas and while the web apps we use to demonstrate their construction can help make sense of a single "dot" on the distribution, students commonly lose the forest for the trees. Wild et al (2017) proposed the use of scaffolded animations to help students hone their intuition about sampling/randomization variation and to discover the utility of the bootstrap and permutation distributions. While the animations discussed by Wild et al (2017) to visualize randomization variation appear to be quite useful in communicating this complex idea to students, a "formal" distribution is not necessary to introduce the core ideas behind hypothesis testing.…”

“…Wild et al (2017) proposed the use of scaffolded animations to help students hone their intuition about sampling/randomization variation and to discover the utility of the bootstrap and permutation distributions. While the animations discussed by Wild et al (2017) to visualize randomization variation appear to be quite useful in communicating this complex idea to students, a "formal" distribution is not necessary to introduce the core ideas behind hypothesis testing. As an alternative, we propose use of the lineup protocol ( Buja et al 2009) to visually introduce the logic behind hypothesis tests and to help students differentiate signal from noise as they meet new plots.…”

Bringing Visual Inference to the Classroom

“…These distributions are very abstract ideas and while the web apps we use to demonstrate their construction can help make sense of a single "dot" on the distribution, students commonly lose the forest for the trees. Wild et al (2017) proposed the use of scaffolded animations to help students hone their intuition about sampling/randomization variation and to discover the utility of the bootstrap and permutation distributions. While the animations discussed by Wild et al (2017) to visualize randomization variation appear to be quite useful in communicating this complex idea to students, a "formal" distribution of is not necessary to introduce the core ideas behind hypothesis testing.…”

“…Wild et al (2017) proposed the use of scaffolded animations to help students hone their intuition about sampling/randomization variation and to discover the utility of the bootstrap and permutation distributions. While the animations discussed by Wild et al (2017) to visualize randomization variation appear to be quite useful in communicating this complex idea to students, a "formal" distribution of is not necessary to introduce the core ideas behind hypothesis testing. Instead, we can ask students to try to identify the data plot among a small set of decoy plots generated by permutation resampling and link this simple perceptual task with fundamental ideas of statistical inference.…”