Modeling as a Core Component of Structuring Data

Abstract

We gave participants diagrams of traffic on two roads with information about eight attributes, including the type of each vehicle, its speed, direction and the width of the road. Their task was to record and organize the data to assist city planners in its analysis. Successfully encoding the information required the creation of a case, a physical record of one repetition of a repeatable observational process. We analyzed data sheets participants created including the methods they used to bind information together into cases. Overall, 79% of their data sheets successfully encoded the data. Even 62% of the middle school students were able to create a bound structure that could hold the critical information from the diagrams. A majority of these structures involved a hierarchy of cases rather than the “flat” case-by-attribute structure that virtually all statistical software require. Our sense is that participants strove to create a structure that modeled the real-world as closely as they could, constructing cases that corresponded to the different sorts of objects they perceived—vehicles with their characteristics nested within road segments with their characteristics.
 First published November 2017 at Statistics Education Research Journal Archives

Designing a sequence of activities to build reasoning about data and visualization

“…From observations and data collected during Activity 3, we found that the tidy data structure was not how most teachers naturally structure data. This is consistent with Konold et al's [19] findings that both children and adults typically struggled to determine how to structure their data. Comments from the teachers suggest that they saw the tidy structure as “necessary for interacting with computers” rather than as a tool to reason about data semantics.…”

“…To culminate the session, the teachers were shown the Traffic Visualization depiction (see Figure 8) created by Konold et al [19] and were asked to extract the data contained in the visualization and structure it using the tidy principles. They continued to work in small groups to create tidy data structures to capture the information presented in the visual.…”

“…Providing students with multivariate reasoning through data and data structures has proven significantly more challenging. Perhaps stemming from a lack of practice or inherent difficulties, creating and utilizing data structures to store and represent multivariate relationships is challenging not only for young students, but also for adults (eg, [19]).…”

Insights from DataFest point to new opportunities for undergraduate statistics courses: Team collaborations, designing research questions, and data ethics

“…From prior research, we know that there are many dimensions and challenges to supporting students' ability to reason statistically [13,23] as well as challenges to developing data literacy and acumen [9,17,21]. For the purposes of this paper, we focus on the three components we see as critical to developing in introductory statistics and data science courses: (1) developing a research question when working with messy, complex data that was not collected by the analyst, (2) professional ethics and personal bias, and (3) collaborative problem-solving.…”

How learners produce data from text in classifying clickbait

“…How can such “messy‐data” be represented? Konold, Finzer, and Kreetong [19], who defined a “case” as “the physical record of one repetition of a repeatable observational process,” noted that data are typically recorded in table format. This immediately raises important questions regarding text as data, since text is obviously stored as data on a computer, but its underlying phenomena (meaning) are of interest rather than specific encodings.…”