Inspired by the author's need for practical guidance in the processes of data analysis, A Practical Guide to Scientific Data Analysis has been written as a statistical companion for the working scientist. This handbook of data analysis with worked examples focuses on the application of mathematical and statistical techniques and the interpretation of their results.
Covering the most common statistical methods for examining and exploring relationships in data, the text includes extensive examples from a variety of scientific disciplines.
The chapters are organised logically, from planning an experiment, through examining and displaying the data, to constructing quantitative models. Each chapter is intended to stand alone so that casual users can refer to the section that is most appropriate to their problem.
Written by a highly qualified and internationally respected author this text:
- Presents statistics for the non-statistician
- Explains a variety of methods to extract information from data
- Describes the application of statistical methods to the design of “performance chemicals”
- Emphasises the application of statistical techniques and the interpretation of their results
Of practical use to chemists, biochemists, pharmacists, biologists and researchers from many other scientific disciplines in both industry and academia.
Author(s): David J. Livingstone
Edition: 1
Publisher: Wiley
Year: 2009
Language: English
Pages: 360
City: Chichester, U.K
Tags: Информатика и вычислительная техника;Искусственный интеллект;Интеллектуальный анализ данных;
A Practical Guide to
Scientific Data Analysis......Page 4
Contents......Page 10
Preface......Page 14
Abbreviations......Page 16
1 Introduction: Data and Its Properties, Analytical Methods and Jargon......Page 20
1.1 Introduction......Page 21
1.2 Types of Data......Page 22
1.3.1 Dependent Data......Page 24
1.3.2 Independent Data......Page 25
1.4 The Nature of Data......Page 26
1.4.1 Types of Data and Scales of Measurement......Page 27
1.4.2 Data Distribution......Page 29
1.4.3 Deviations in Distribution......Page 34
1.5 Analytical Methods......Page 38
References......Page 42
2.1 What is Experimental Design?......Page 44
2.2 Experimental Design Techniques......Page 46
2.2.1 Single-factor Design Methods......Page 50
2.2.2 Factorial Design (Multiple-factor Design)......Page 52
2.2.3 D-optimal Design......Page 57
2.3 Strategies for Compound Selection......Page 59
2.4 High Throughput Experiments......Page 70
2.5 Summary......Page 72
References......Page 73
3.1 Introduction......Page 76
3.2 Data Distribution......Page 77
3.3 Scaling......Page 79
3.4 Correlations......Page 81
3.5 Data Reduction......Page 82
3.6 Variable Selection......Page 86
3.7 Summary......Page 91
References......Page 92
4.1 Introduction......Page 94
4.2 Linear Methods......Page 96
4.3.1 Nonlinear Mapping......Page 113
4.3.2 Self-organizing Map......Page 124
4.4 Faces, Flowerplots and Friends......Page 129
4.5 Summary......Page 132
References......Page 135
5.1 Introduction......Page 138
5.2 Nearest-neighbour Methods......Page 139
5.3 Factor Analysis......Page 144
5.4 Cluster Analysis......Page 154
5.5 Cluster Significance Analysis......Page 159
5.6 Summary......Page 162
References......Page 163
6.1 Introduction......Page 164
6.2 Simple Linear Regression......Page 165
6.3 Multiple Linear Regression......Page 173
6.3.1.1 Forward Inclusion......Page 178
6.3.1.2 Backward Elimination......Page 180
6.3.1.3 Stepwise Regression......Page 182
6.3.1.4 All Subsets......Page 183
6.3.1.5 Model Selection by Genetic Algorithm......Page 184
6.3.2 Nonlinear Regression Models......Page 186
6.3.3 Regression with Indicator Variables......Page 188
6.4.1 Robustness (Cross-validation)......Page 193
6.4.2 Chance Effects......Page 196
6.4.3 Comparison of Regression Models......Page 198
6.4.4 Selection Bias......Page 199
6.5 Summary......Page 202
References......Page 203
7.1 Introduction......Page 206
7.2.1 Discriminant Analysis......Page 207
7.2.2 SIMCA......Page 214
7.2.3 Confusion Matrices......Page 217
7.2.4 Conditions and Cautions for Discriminant Analysis......Page 220
7.3 Regression on Principal Components and PLS......Page 221
7.3.1 Regression on Principal Components......Page 222
7.3.2 Partial Least Squares......Page 225
7.3.3 Continuum Regression......Page 230
7.4 Feature Selection......Page 233
7.5 Summary......Page 235
References......Page 236
8.1 Introduction......Page 238
8.2 Principal Components and Factor Analysis......Page 240
8.3 Cluster Analysis......Page 249
8.4 Spectral Map Analysis......Page 252
8.5 Models with Multivariate Dependent and Independent Data......Page 257
8.6 Summary......Page 265
References......Page 266
9 Artificial Intelligence and Friends......Page 268
9.1 Introduction......Page 269
9.2 Expert Systems......Page 270
9.2.1 Log P Prediction......Page 271
9.2.2 Toxicity Prediction......Page 280
9.2.3 Reaction and Structure Prediction......Page 287
9.3 Neural Networks......Page 292
9.3.1 Data Display Using ANN......Page 296
9.3.2 Data Analysis Using ANN......Page 299
9.3.3 Building ANN Models......Page 306
9.3.4 Interrogating ANN Models......Page 311
9.4 Miscellaneous AI Techniques......Page 314
9.5 Genetic Methods......Page 320
9.6 Consensus Models......Page 322
9.7 Summary......Page 323
References......Page 324
10.1 The Need for Molecular Design......Page 328
10.2 What is QSAR/QSPR?......Page 329
10.3 Why Look for Quantitative Relationships?......Page 340
10.4 Modelling Chemistry......Page 342
10.5 Molecular Field and Surface Descriptors......Page 344
10.6 Mixtures......Page 346
10.7 Summary......Page 348
References......Page 349
Index......Page 352
