Mark P. Kritzman - Prediction Revisited

1 Cover

2 Title Page PREDICTION REVISITED THE IMPORTANCE OF OBSERVATION MEGAN CZASONIS MARK KRITZMAN DAVID TURKINGTON

3 Copyright

4 Timeline of Innovations

5 Essential Concepts

6 Preface

7 1 Introduction Relevance Roadmap Note

8 2 Observing Information Observing Information Conceptually Observing Information Mathematically Observing Information Applied Appendix 2.1: On the Inflection Point of the Normal Distribution References Notes

9 3 Co-occurrence Co-occurrence Conceptually Co-occurrence Mathematically Co-occurrence Applied References Note

10 4 Relevance Relevance Conceptually Relevance Mathematically Relevance Applied Appendix 4.1: Predicting Binary Outcomes References Notes

11 5 Fit Fit Conceptually Fit Mathematically Fit Applied Notes

12 6 Reliability Reliability Conceptually Reliability Mathematically Reliability Applied References Notes

13 7 Toward Complexity Toward Complexity Conceptually Toward Complexity Mathematically Complexity Applied References

14 8 Foundations of Relevance Observations and Relevance: A Brief Review of the Main Insights Abraham de Moivre (1667–1754) Pierre-Simon Laplace (1749–1827) Carl Friedrich Gauss (1777–1853) Francis Galton (1822–1911) Karl Pearson (1857–1936) Ronald Fisher (1890–1962) Prasanta Chandra Mahalanobis (1893–1972) Claude Shannon (1916–2001) References Notes

15 Concluding Thoughts Perspective Insights Prescriptions

16 Index

17 End User License Agreement

1 Chapter 2Exhibit 2.5 DatasetExhibit 2.6 Arithmetic AveragesExhibit 2.9 Pairwise Spreads and Variance Calculation—Industrial Production...Exhibit 2.10 Conventional Variance Calculation—Industrial Production...Exhibit 2.11 Arithmetic Averages, Variances, and Standard DeviationsExhibit 2.12 Flipping 10 Coins

2 Chapter 3Exhibit 3.4 Correlation MatrixExhibit 3.6 Pairwise z-scores for Individual AttributesExhibit 3.7 Pairwise Co-occurrence—Industrial Production and Nonfarm Payrol...Exhibit 3.8 Information Distance of Pairwise Co-occurrence—Industrial Produ...Exhibit 3.9 Pairwise Correlation Calculation—Industrial Production and Nonf...Exhibit 3.11 Conventional Correlation Calculation—Industrial Production and...Exhibit 3.12 Correlation MatrixExhibit 3.13 Covariance Matrix

3 Chapter 4Exhibit 4.9 Observations and Their Relevance to Exhibit 4.11 Relevance-Weighted Outcomes and Full-Sample Regression Predict...Exhibit 4.13 Conventional Full-Sample Regression PredictionExhibit 4.15 Partial Sample Prediction CalculationExhibit 4.16 Asymmetry Calculation for PredictionExhibit 4.17 Aggregate Asymmetry Calculation

4 Chapter 5Exhibit 5.3 Pairwise Relevance and OutcomesExhibit 5.4 Prediction FitExhibit 5.5 Prediction Variance and BoundsExhibit 5.6 PrecisionExhibit 5.7 Calculating Prediction Fit for Partial Sample PredictionExhibit 5.8 Prediction Variance, Bounds, and Precision for Partial Sample P...

5 Chapter 6Exhibit 6.3 Calculating ReliabilityExhibit 6.4 Pairwise Relevance and Pairwise OutcomesExhibit 6.5 Pairwise Calculation of Full-Sample ReliabilityExhibit 6.6 Traditional Approach to Calculating R-squaredExhibit 6.7 Calculating Reliability for Partial Sample RegressionExhibit 6.9 Removing the Impact of Biased TermsExhibit 6.10 Addressing the Bias of R-Squared

6 Chapter 8Exhibit 8.1 Binomial Distribution

1 Chapter 2Exhibit 2.1 SpreadsExhibit 2.2 Triangle of PairsExhibit 2.3 Subsequent GDP GrowthExhibit 2.4 Trailing Percentage Changes in Industrial ProductionExhibit 2.7 Industrial ProductionExhibit 2.8 Histogram of Industrial ProductionExhibit 2.13 Distribution of CombinationsExhibit 2.14 Counting Distinct Combinations for 30 Trials

2 Chapter 3Exhibit 3.1 Two Positively Related Attributes for a Single ObservationExhibit 3.2 Possible Co-occurrence Patterns for Attributes with a Given Aver...Exhibit 3.3 Co-occurrence for Single ObservationsExhibit 3.5 Pairs of Pairs Approach for Estimating Co-occurrenceExhibit 3.10 Pairwise Co-occurrence—Industrial Production and Nonfarm Payrol...

3 Chapter 4Exhibit 4.1 Scatter Plot of Two Hypothetical AttributesExhibit 4.2 Similarity, Informativeness, and Relevance of Hypothetical Obser...Exhibit 4.3 Simulated Symmetric RelationshipExhibit 4.4 Predictions versus Actual OutcomesExhibit 4.5 Simulated Asymmetric RelationshipExhibit 4.6 Predictions versus Actual OutcomesExhibit 4.7 Informativeness and Similarity with Two AttributesExhibit 4.8 Equally Informative Observations with Five AttributesExhibit 4.10 Relevance of Observations to Exhibit 4.12 Outcome Deviations from AverageExhibit 4.14 Relevance and Outcome Deviations—25% Most Relevant Observations...Exhibit 4.18 AsymmetryExhibit 4.19 Logistic FunctionExhibit 4.20 Logit Function (inverse of the logistic function)

4 Chapter 5Exhibit 5.1 Relevance and Outcomes for a Very Good Partial FitExhibit 5.2 Pairwise Relevance and Fit

5 Chapter 6Exhibit 6.1 Components of Fit for Simulated Random NoiseExhibit 6.2 Components of Fit for Simulated Random NoiseExhibit 6.8 Reliability of Partial Sample Regression

6 Chapter 7Exhibit 7.1 Decision Tree

7 Chapter 8Exhibit 8.2 Galton's Quincunx

1 Cover

2 Table of Contents

3 Title Page

4 Copyright

5 Timeline of Innovations

6 Essential Concepts

7 Preface

8 Begin Reading

9 Concluding Thoughts

10 Index

11 End User License Agreement

1 iii

2 iv

3 ix

4 xi

5 xii

6 xiii

7 xiv

8 xv

9 xvi

10 xvii

11 1

12 2

13 3

14 4

15 5

16 7

17 8

18 9

19 10

20 11

21 12

22 13

23 14

24 15

25 16

26 17

27 18

28 19

29 20

30 21

31 22

32 23

33 24

34 25

35 26

36 27

37 28

38 29

39 30

40 31

41 32

42 33

43 34

44 35

45 36

46 37

47 38

48 39

49 41

50 42

51 43

52 44

53 45

54 46

55 47

56 48

57 49

58 50

59 51

60 52

61 53

62 54

63 55

64 56

65 57

66 58

67 59

68 60

69 61

70 62

71 63

72 64

73 65

74 66

75 67

76 68

77 69

78 70

79 71

80 72

81 73

82 74

83 75

84 76

85 77

86 78

87 79

88 80

89 81

90 82

91 83

92 84

93 85

94 86

95 87

96 88

97 89

98 90

99 91

100 92

101 93

102 94

103 95

104 96

105 97

106 98

107 99

108 100

109 101

110 102

111 103

112 104

113 105

114 106

115 107

116 108

117 109

118 110

119 111

120 112

121 113

122 114

123 115

124 116

125 117

126 118

127 119

128 120

129 121

130 123

131 124

132 125

133 126

134 127

135 128

136 129

137 130

138 131

139 132