Presentation is loading. Please wait.

Presentation is loading. Please wait.

Dr. Michael R. Hyman, NMSU Chart Deception Main Source: How to Lie with Charts, by Gerald E. Jones.

Similar presentations


Presentation on theme: "Dr. Michael R. Hyman, NMSU Chart Deception Main Source: How to Lie with Charts, by Gerald E. Jones."— Presentation transcript:

1 Dr. Michael R. Hyman, NMSU Chart Deception Main Source: How to Lie with Charts, by Gerald E. Jones

2 2 Information Information = Data + Labels =data (505) =information

3 3 Summaries Can Hide Needed Detail

4 4

5 5 Pie Charts Pie charts denote percentages Label slices with percentages, not raw values –True of two pie figures Most important slice –Right-hand slice –Exploded slice Bottom slice of 3-D pie seems overly important

6 6

7 7

8 8

9 9 Pie Charts Pie charts denote percentages Label slices with percentages, not raw values –True of two pie figures Most important slice –Right-hand slice –Exploded slice Bottom slice of 3-D pie seems overly important

10 10

11 11 Pie Charts Pie charts denote percentages Label slices with percentages, not raw values –True of two pie figures Most important slice –Right-hand slice –Exploded slice Bottom slice of 3-D pie seems overly important

12 12

13 13 Pie Charts Pie charts denote percentages Label slices with percentages, not raw values –True of two pie figures Most important slice –Right-hand slice –Exploded slice Bottom slice of 3-D pie seems overly important

14 14

15 15 Pie Charts Multi-sized pies on same figure (to denote trend) biased by dissimilar diameter-area rates of growth Large ‘Other’ slice can hide needed detail Use pie-column chart for more detail on a slice Donut charts confusing Omitting missing data increases relate size of all slices

16 16

17 17 Pie Charts Multi-sized pies on same figure (to denote trend) biased by dissimilar diameter-area rates of growth Large ‘Other’ slice can hide needed detail Use pie-column chart for more detail on a slice Donut charts confusing Omitting missing data increases relate size of all slices

18 18

19 19 Pie Charts Multi-sized pies on same figure (to denote trend) biased by dissimilar diameter-area rates of growth Large ‘Other’ slice can hide needed detail Use pie-column chart for more detail on a slice Donut charts confusing Omitting missing data increases relate size of all slices

20 20

21 21 Pie Charts Multi-sized pies on same figure (to denote trend) biased by dissimilar diameter-area rates of growth Large ‘Other’ slice can hide needed detail Use pie-column chart for more detail on a slice Donut charts confusing Omitting missing data increases relate size of all slices

22 22

23 23 Attend to Cultural Bias in Orienting Charts

24 24

25 25

26 26 Argo Sales Increase Sales, in units or dollars, listed along the y axis Avoid 3D effects

27 27

28 28 Bar Chart—Avoid 3D and Sideways

29 29

30 30

31 31

32 32

33 33 Bar and Area Charts Stacked vs. clustered bar charts –Mixing cumulative and clustered bars can confuse viewers When stacking, place least variable component on bottom Avoid paired-bar charts Viewers can misread 3-D bars

34 34

35 35

36 36

37 37 Bar and Area Charts Stacked vs. clustered bar charts –Mixing cumulative and clustered bars can confuse viewers When stacking, place least variable component on bottom Avoid paired-bar charts Viewers can misread 3-D bars

38 38

39 39 Bar and Area Charts Stacked vs. clustered bar charts –Mixing cumulative and clustered bars can confuse viewers When stacking, place least variable component on bottom Avoid paired-bar charts Viewers can misread 3-D bars

40 40

41 41 Bar and Area Charts Stacked vs. clustered bar charts –Mixing cumulative and clustered bars can confuse viewers When stacking, place least variable component on bottom Avoid paired-bar charts Viewers can misread 3-D bars

42 42

43 43 Bar Graph—Avoid 3D

44 44 Avoid 3-D Effects

45 45

46 46 Line Graph—Avoid 3D

47 47

48 48 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

49 49

50 50

51 51 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

52 52

53 53

54 54

55 55

56 56 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

57 57

58 58

59 59 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

60 60

61 61

62 62 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

63 63

64 64

65 65 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

66 66

67 67

68 68

69 69 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

70 70

71 71 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

72 72

73 73 XY (or Scatter) Charts Label data points Start axes at coordinates (0,0) Avoid distorting axes Avoid broken axes Cumulative charts seem optimistic because upward sloping Avoid dissimilar data on same chart Semi-log charts can minimize trends If x axis isn’t time axis, connecting dots can mistakenly suggest a trend Interpolation and extrapolation are subjective

74 74 Radar Charts Beware non-uniform scales on axes

75 75

76 76 Depicting Confidence Intervals

77 77

78 78

79 79

80 80 Headers and Footers Use footnotes to source table (avoid plagiarism charge) Font rules –Use proportional font –Don’t mix fonts in a chart –Use upper and lower case letters Spell out numbers 1 through 9 unless a measure

81 81

82 82 Examples of Bad Graphics

83 83

84 84

85 85

86 86

87 87 Examples of Bad and Better Graphics

88 88 Example #1

89 89

90 90 Example #2

91 91

92 92 Example #3

93 93

94 94 Example #4

95 95

96 96 Example #5

97 97

98 98 Example #6

99 99

100 100 Example #7

101 101

102 102 Example #8

103 103

104 104


Download ppt "Dr. Michael R. Hyman, NMSU Chart Deception Main Source: How to Lie with Charts, by Gerald E. Jones."

Similar presentations


Ads by Google