Read more
Informationen zum Autor David J. Livingstone is the author of A Practical Guide to Scientific Data Analysis, published by Wiley. Klappentext A practical handbook aimed at the working scientist, it covers the application of statistical and mathematical methods to the design of "performance" chemicals, such as pharmaceuticals, agrochemicals, fragrances, flavours and paints. This volume will have wide appeal, not only to chemists, but biochemists, pharmacists and other researchers within the field of statistical analysis of experimental results.* The first book in this field to address this topic* The statistics book for the non-statistician* Highly qualified and internationally respected author Zusammenfassung A practical handbook aimed at the working scientist, it covers the application of statistical and mathematical methods to the design of "performance" chemicals, such as pharmaceuticals, agrochemicals, fragrances, flavours and paints. This volume will have wide appeal, not only to chemists, but biochemists, pharmacists and other researchers within the field of statistical analysis of experimental results.* The first book in this field to address this topic* The statistics book for the non-statistician* Highly qualified and internationally respected author Inhaltsverzeichnis Preface xi Abbreviations xiii 1 Introduction: Data and Its Properties, Analytical Methods and Jargon 1 1.1 Introduction 2 1.2 Types of Data 3 1.3 Sources of Data 5 1.3.1 Dependent Data 5 1.3.2 Independent Data 6 1.4 The Nature of Data 7 1.4.1 Types of Data and Scales of Measurement 8 1.4.2 Data Distribution 10 1.4.3 Deviations in Distribution 15 1.5 Analytical Methods 19 1.6 Summary 23 References 23 2 Experimental Design - Experiment and Set Selection 25 2.1 What is Experimental Design? 25 2.2 Experimental Design Techniques 27 2.2.1 Single-factor Design Methods 31 2.2.2 Factorial Design (Multiple-factor Design) 33 2.2.3 D-optimal Design 38 2.3 Strategies for Compound Selection 40 2.4 High Throughput Experiments 51 2.5 Summary 53 References 54 3 Data Pre-treatment and Variable Selection 57 3.1 Introduction 57 3.2 Data Distribution 58 3.3 Scaling 60 3.4 Correlations 62 3.5 Data Reduction 63 3.6 Variable Selection 67 3.7 Summary 72 References 73 4 Data Display 75 4.1 Introduction 75 4.2 Linear Methods 77 4.3 Nonlinear Methods 94 4.3.1 Nonlinear Mapping 94 4.3.2 Self-organizing Map 105 4.4 Faces, Flowerplots and Friends 110 4.5 Summary 113 References 116 5 Unsupervised Learning 119 5.1 Introduction 119 5.2 Nearest-neighbour Methods 120 5.3 Factor Analysis 125 5.4 Cluster Analysis 135 5.5 Cluster Significance Analysis 140 5.6 Summary 143 References 144 6 Regression Analysis 145 6.1 Introduction 145 6.2 Simple Linear Regression 146 6.3 Multiple Linear Regression 154 6.3.1 Creating Multiple Regression Models 159 6.3.1.1 Forward Inclusion 159 6.3.1.2 Backward Elimination 161 6.3.1.3 Stepwise Regression 163 6.3.1.4 All Subsets 164 6.3.1.5 Model Selection by Genetic Algorithm 165 6.3.2 Nonlinear Regression Models 167 6.3.3 Regression with Indicator Variables 169 6.4 Multiple Regression: Robustness, Chance Effects, the Comparison of Models and Selection Bias 174 6.4.1 Robustness (Cross-validation) 174 6.4.2 Chance Effects 177 6.4.3 Comparison of Regression Models 178 6.4.4 Selection Bias 180 6.5 Summary 183 References 184 7 Supervised Learning 187 7.1 Introduction 187 7.2...
