2-3 Graphs That Enlighten and Graphs That Deceive 67 Graphs That Deceive Deceptive graphs are commonly used to mislead people, and we really don’t want statistics students to be among those susceptible to such deceptions. Graphs should be constructed in a way that is fair and objective. The readers should be allowed to make their own judgments, instead of being manipulated by misleading graphs. We present two of the ways in which graphs are commonly used to misrepresent data. Nonzero Vertical Axis A common deceptive graph involves using a vertical scale that starts at some value greater than zero to exaggerate differences between groups. FIGURE 2-11 Relative Frequency Polygons for Commute Time in Los Angeles and Boise (minutes) NONZERO AXIS Always examine a graph carefully to see whether a vertical axis begins at some point other than zero so that differences are exaggerated. Nonzero Axis EXAMPLE 8 Figure 2-12(a) and Figure 2-12(b) on the next page are based on the same data from a clinical trial of OxyContin (oxycodone), a drug used to treat moderate to severe pain. The results of that clinical trial included the percentage of subjects who experienced nausea in an OxyContin treatment group and the percentage in a group given a placebo. By using a vertical scale that starts at 10% instead of 0%, Figure 2-12(a) grossly exaggerates the difference between the two groups. Figure 2-12(a) makes it appear that those using OxyContin experience nausea at a rate that is about 12 times higher than the rate for those using a placebo, but Figure 2-12(b) shows that the true ratio is about 2:1, not 12:1. Perhaps someone wants to discourage recreational use of OxyContin by misleading people into thinking that the problem with nausea is much greater than it really is. The objective might be sincere, but the use of a misleading graph is not the way to achieve that objective. YOUR TURN. Do Exercise 17 “Self-Driving Vehicles.” Go Figure 4,574,150,134: Number of Internet users in the world.
RkJQdWJsaXNoZXIy NjM5ODQ=