Developing Consistency in the Terminology and Display of Bar Graphs and Histograms

Humphrey, Patricia B.; Taylor, Sharon; Mittag, Kathleen Cage

doi:10.1111/test.12030

Cited by 9 publications

(13 citation statements)

References 5 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…42 Each bar represents a category; shape can be changed by moving the categories around. 25 Useful for understanding distributions from large datasets. 42 .…”

Section: Additional Suggestions For Implementationmentioning

confidence: 99%

See 1 more Smart Citation

Development of a framework for graph choice and construction

Angra

Gardner

2016

Advances in Physiology Education

View full text Add to dashboard Cite

COLLECTING, understanding, and interpreting data are key skills that all students should master (8,12,22, 33). Research on graph interpretation and basic construction is extensive, and student difficulties, primarily in K-12 type settings, have been well documented [e.g., graph choice (30,32,45), labels for axes (30,32), variables (45), and scaling axes (1,7,32,34)].Although many instructional books exist on graphing (5, 20, 28, 47), they do not focus on the complex reasoning behind graph choice and construction. It is insufficient to choose an appropriate graph for data (e.g., bar graph for categorical data) without evaluating the advantages and disadvantages of using a particular graph.Metarepresentational competence (MRC) refers to the knowledge required for successful construction and reasoning with external representations, which includes graphs ( 14). MRC has several components that reveal students' ability and inability with graph choice, construction, and critique (15). Specifically, these areas are invention, critique, functioning, and learning or reflection (Table 1) (15). The first area, invention, reveals students' underlying skills and abilities that allow them to conceive novel graphical representations from data (15). The second area, critique, exposes students' critical knowledge that is essential for assessing various types of graphs and their strengths and weaknesses (15). The third area, functioning, unearths students' reasoning for understanding the purpose of different types of graphs and the usage being dependent on the type of data present (15). The final area, learning or reflection, reveals students' awareness of their own understanding of graphs (15).

show abstract

“…42 Each bar represents a category; shape can be changed by moving the categories around. 25 Useful for understanding distributions from large datasets. 42 .…”

Section: Additional Suggestions For Implementationmentioning

confidence: 99%

“…To show a distribution of data with the independent variable as continuous. 25 Uses numerical data instead of categorical data 25 .…”

Section: Histogrammentioning

confidence: 99%

Development of a framework for graph choice and construction

Angra

Gardner

2016

Advances in Physiology Education

View full text Add to dashboard Cite

show abstract

“…But are those pictures reliable? As must be emphasized (see, for example, Humphrey et al ) different bin widths and/or starting points may produce quite different histograms. So data without any reasonable pattern (like the leftmost parts of figures and ) may be grouped in different ways in order to show increasing behaviour, while the same data might also show decreasing behaviour.…”

Section: Resultsmentioning

confidence: 99%

Two easy ways to cheat

Meyer¹

2017

Teaching Statistics

View full text Add to dashboard Cite

show abstract

“…Consider that typical data visualizations for identifying shape include boxplots, dot plots and histograms. These visualizations are certainly important and should be given priority due to their (1) prevalence as standard modes of representation and (2) adherence to the items suggested by both Few () and Tufte () (see Humphrey et al , for an in depth discussion of consistency of presenting histograms). However, mainstream media outlets, including those focused on weather and those that proclaim to be data based (e.g.…”

Section: What Are Heat Maps?mentioning

confidence: 99%