We compare two methods of recording data and making graphic displays: a standard paper-and-pencil technique and a "data-cards" approach in which students record case information on individual cards which they then arrange to make displays. Students using the data cards produced displays that tended to be more complex and informative than displays made by those in the paper-and-pencil group. We explore plausible explanations for this difference by examining structural aspects of the two approaches, such as the saliency of the case and the use of space in organizing the information. Our results call into question the wisdom of the current practice of introducing young students to particular graph types and of the idea that they need to master handling of univariate data before they move on to multivariate data.
The CAUSE Research Group is supported in part by a member initiative grant from the American Statistical Association’s Section on Statistics and Data Science Education