PREFACE |
|
ix | |
1 A WORKED EXAMPLE |
|
1 | (30) |
|
|
1 | (9) |
|
1.2 Modulus version of the simple model |
|
|
10 | (5) |
|
1.3 Six-factor version of the simple model |
|
|
15 | (7) |
|
1.4 The simple model 'by groups' |
|
|
22 | (3) |
|
1.5 The (less) simple correlated-input model |
|
|
25 | (3) |
|
|
28 | (3) |
2 GLOBAL SENSITWITY ANALYSIS FOR IMPORTANCE ASSESSMENT |
|
31 | (32) |
|
|
31 | (11) |
|
2.2 What is sensitivity analysis? |
|
|
42 | (5) |
|
2.3 Properties of an ideal sensitivity analysis method |
|
|
47 | (2) |
|
2.4 Defensible settings for sensitivity analysis |
|
|
49 | (7) |
|
|
56 | (7) |
3 TEST CASES |
|
63 | (28) |
|
3.1 The jumping man. Applying variance-based methods |
|
|
63 | (3) |
|
3.2 Handling the risk of a financial portfolio: the problem of hedging. Applying Monte Carlo filtering and variance-based methods |
|
|
66 | (5) |
|
3.3 A model of fish population dynamics. Applying the method of Morris |
|
|
71 | (6) |
|
3.4 The Level E model. Radionuclide migration in the geosphere. Applying variance-based methods and Monte Carlo filtering |
|
|
77 | (6) |
|
3.5 Two spheres. Applying variance based methods in estimation/calibration problems |
|
|
83 | (2) |
|
3.6 A chemical experiment. Applying variance based methods in estimation/calibration problems |
|
|
85 | (3) |
|
3.7 An analytical example. Applying the method of Morris |
|
|
88 | (3) |
4 THE SCREENING EXERCISE |
|
91 | (18) |
|
|
91 | (3) |
|
|
94 | (6) |
|
4.3 Implementing the method |
|
|
100 | (3) |
|
4.4 Putting the method to work: an analytical example |
|
|
103 | (1) |
|
4.5 Putting the method to work: sensitivity analysis of a fish population model |
|
|
104 | (3) |
|
|
107 | (2) |
5 METHODS BASED ON DECOMPOSING THE VARIANCE OF THE OUTPUT |
|
109 | (42) |
|
|
109 | (1) |
|
5.2 Factors Prioritisation Setting |
|
|
110 | (1) |
|
5.3 First-order effects and interactions |
|
|
111 | (1) |
|
5.4 Application of Si to Setting 'Factors Prioritisation' |
|
|
112 | (6) |
|
5.5 More on variance decompositions |
|
|
118 | (2) |
|
5.6 Factors Fixing (FF) Setting |
|
|
120 | (1) |
|
5.7 Variance Cutting (VC) Setting |
|
|
121 | (2) |
|
5.8 Properties of the variance based methods |
|
|
123 | (1) |
|
5.9 How to compute the sensitivity indices: the case of orthogonal input |
|
|
124 | (24) |
|
5.9.1 A digression on the Fourier Amplitude Sensitivity Test (FAST) |
|
|
132 | (1) |
|
5.10 How to compute the sensitivity indices: the case of non-orthogonal input |
|
|
132 | (4) |
|
5.11 Putting the method to work: the Level E model |
|
|
136 | (9) |
|
5.11.1 Case of orthogonal input factors |
|
|
137 | (7) |
|
5.11.2 Case of correlated input factors |
|
|
144 | (1) |
|
5.12 Putting the method to work: the bungee jumping model |
|
|
145 | (3) |
|
|
148 | (3) |
6 SENSITIVITY ANALYSIS IN DIAGNOSTIC MODELLING: MONTE CARLO FILTERING AND REGIONALISED SENSITIVITY ANALYSIS, BAYESIAN UNCERTAINTY ESTIMATION AND GLOBAL SENSITIVITY ANALYSIS |
|
151 | (42) |
|
6.1 Model calibration and Factors Mapping Setting |
|
|
151 | (2) |
|
6.2 Monte Carlo filtering and regionalised sensitivity analysis |
|
|
153 | (8) |
|
|
155 | (6) |
|
6.3 Putting MC filtering and RSA to work: the problem of hedging a financial portfolio |
|
|
161 | (6) |
|
6.4 Putting MC filtering and RSA to work: the Level E test case |
|
|
167 | (3) |
|
6.5 Bayesian uncertainty estimation and global sensitivity analysis |
|
|
170 | (8) |
|
6.5.1 Bayesian uncertainty estimation |
|
|
170 | (3) |
|
|
173 | (2) |
|
6.5.3 Using global sensitivity analysis in the Bayesian uncertainty estimation |
|
|
175 | (3) |
|
6.5.4 Implementation of the method |
|
|
178 | (1) |
|
6.6 Putting Bayesian analysis and global SA to work: two spheres |
|
|
178 | (6) |
|
6.7 Putting Bayesian analysis and global SA to work: a chemical experiment |
|
|
184 | (7) |
|
6.7.1 Bayesian uncertainty analysis (GLUE case) |
|
|
185 | (1) |
|
6.7.2 Global sensitivity analysis |
|
|
185 | (3) |
|
6.7.3 Correlation analysis |
|
|
188 | (1) |
|
6.7.4 Further analysis by varying temperature in the data set: fewer interactions in the model |
|
|
189 | (2) |
|
|
191 | (2) |
7 HOW TO USE SIMLAG |
|
193 | (12) |
|
|
193 | (1) |
|
7.2 How to obtain and install SIMLAG |
|
|
194 | (1) |
|
|
194 | (3) |
|
|
197 | (4) |
|
|
198 | (1) |
|
|
198 | (1) |
|
7.4.3 Latin hypercube sampling (LHS) |
|
|
198 | (1) |
|
7.4.4 The method of Morris |
|
|
199 | (1) |
|
|
199 | (1) |
|
|
200 | (1) |
|
7.4.7 Replicated Latin Hypercube (r-LHS) |
|
|
200 | (1) |
|
7.4.8 The method of Sobol' |
|
|
200 | (1) |
|
7.4.9 How to induce dependencies in the input factors |
|
|
200 | (1) |
|
7.5 How to execute models |
|
|
201 | (1) |
|
|
202 | (3) |
8 FAMOUS QUOTES: SENSITIVITY ANALYSIS IN THE SCIENTIFIC DISCOURSE |
|
205 | (6) |
REFERENCES |
|
211 | (6) |
INDEX |
|
217 | |