• Graphical integrity

    普通类
    • 支持
    • 批判
    • 提问
    • 解释
    • 补充
    • 删除
    • Introduction

    GRAPHICAL INTEGRIGY BEGINS WITH TELLING THE TRUTH about the data. All too often graphs are used to confuse or deceive the unwary or naive viewer. Excellent graphs, those with graphical integrity, withstand such scrutiny and truthfully inform the viewer. They effectively explore complicated data and are tools for learning about, and gaining insight into, quantitative information.

    • Graphs of Monetary Measurements

    Click Graph to Correct for Inflation and Population Growth


    Tufte (2001) states as a basic principle of Graphical Integrity:

    In time-series displays of money, deflated and stardardized units of monetary measurements are nearly always better than nominal units.

    One of the most common graphs is of government spending over time. These generally create the impression that spending is rapidly increasing.

    The graph on the right is initially guilty of two statistical failings. First, the graph uses dollars not corrected for inflation. This causes changes in the value of money to be confused with changes in the budget. Correcting for an inflation rate of 5% results in the flatter increase in spending in the second version of the graph.

    Second, no accounting for the potential increase in state population is made. The budget growth may merely reflect population growth. An annual growth rate of 5% results in the almost flat per capita increase in spending of the third version of the graph.

    • Keeping Data in Context

    Click Graph to put Data in Different Contexts


    Graphics often deceive by omission, leaving out information needed for comparison. Tufte (2001) states another principle of Graphical Integrity, "Graphics must not quote data out of context."

    The initial view of the graph on the right fails to provide any truly useful information. Adding data, any data, would add immensely to the value of the graph.

    Filling in the surrounding data, to put the original graph into context is illuminating. Very different interpretations of the data are possible, depending on the context.

    • More Information

    •Choosing the Right Graph 
    •Misrepresenting Data 
    •Comparison Graphs 
    •Graph Labels

    • Author


    Christopher Childs

    Childs, C. (2005). Graphical Integrity. In B. Hoffman (Ed.), Encyclopedia of Educational Technology.

    • 标签:
    • integrity
    • graphs
    • spending
    • data
    • graphical
    • graph.
    • right
    • increase
    • graph
    • population
  • 加入的知识群:
    学习元评论 (0条)

    评论为空
    聪明如你,不妨在这 发表你的看法与心得 ~



    登录之后可以发表学习元评论
      
暂无内容~~
顶部