Nevertheless, a commitment to testing ourselves—actually seeing how well our predictions work in the real world rather than in the comfort of a statistical model—is probably the best way to accelerate the learning process. - Nate Silver, 2012, p. 292
In order to elucidate how cognition can be measured, it is first necessary to define our terms. As previously discussed (see section 1), statistics cognition is purported to be comprised of three components: literacy, reasoning, and thinking (Ben-Zvi & Garfield, 2004; delMas, 2002). Traditionally, these concepts have been used in both scientific and colloquial manners for over 100 years. For example, Fox (1860) rigidly used the term “statistical reasoning” to refer to the ability to understand meaning behind statistical information, whereas Dewey (1891) simply used the term to refer to a skill consisting of “right and honest reasoning” (p. 309). While Dewey’s interpretation of Kenes argued that statistical reasoning should be no less important than teaching individuals how to “manage hygiene”, such conceptualizations of key terms varied drastically in their early use.