Probabilistic sensitivity analysis of complex models: a Bayesian approach

By Jeremy E. Oakley, Anthony OʼHagan. 2004

1,148 citations recorded by the source corpus.

Subfields: Computational Theory and Mathematics, Management Science and Operations Research, Statistics and Probability

View Paper: https://www.semanticscholar.org/paper/44df4b74d004311cec76924f9c6d95fe1c5a0863

How researchers see this paper

The researchers whose trusted networks rank it highest, strongest advocate first. Every researcher gets a different order.

In Computational Theory and Mathematics

In Management Science and Operations Research

In Statistics and Probability

Citations in the corpus

Computer Model Calibration Using High-Dimensional Output (2008, background): “Other marginal functionals of the simulation response can also be calculated such as sensitivity indicies or estimates of the Sobol’ decomposition (Sacks et al. 1989; Oakley and O’Hagan 2004).”
Bayesian emulation of complex multi-output and dynamic computer models (2010, methodology): “Once (6) has been fitted it becomes straightforward to generalise the Bayesian theory of uncertainty and sensitivity analysis given in e.g. Haylock and O’Hagan (1996); Oakley and O’Hagan (2002, 2004) to the multi-output case†.”
Bayesian analysis of computer code outputs: A tutorial (2006, background): “The statistical theory can be found, with full mathematical details, in Kennedy and O’Hagan [1] and Oakley and O’Hagan [4,5].”
Node harvest: simple and interpretable regression and classication (2009, methodology): “While Gaussian process emulation is widely used in this context [Oakley and O’Hagan (2004)], we note that the data here are not (a) ( 15) in the two-dimensional predictor space, with contour lines at values − 1 to 1 with step sizes of 0.2.”
Statistical strategies for avoiding false discoveries in metabolomics and related experiments (2007, background): “…of the prevalence of disease, two or more diagnostic tests can be compared at any or all false positive rates (FPRs), and summary measures of accuracy, such as the AUC, incorporate both components of accuracy, i.e., sensitivity and specificity, into a single measure (Obuchowski et al., 2004).”
The Future of Sensitivity Analysis: An essential discipline for systems modeling and policy support (2020, positive): “…and 2014b), and some Bayesian approaches are already capable of incorporating this uncertainty into posterior distributions of sensitivity measures (Oakley and O ’ Hagan, 2004; Gramacy and Taddy, 2010), further advancements to properly incorporate such uncertainties in SA estimates and respective…”
Sensitivity Analysis for Hydraulic Models (2009, positive): “Emulator meth-ods based on the use of Gaussian processes can yield variance-based sensitivity indices directly (cid:1) Oakley and O’Hagan 2004 (cid:2) .”
Metamodel-based sensitivity analysis: polynomial chaos expansions and Gaussian processes (2016, positive): “1 Analytic formulae The above indices are studied in Oakley and O’Hagan [42] where the estimation of VA and V is performed separately.”
Emulation of a complex global aerosol model to quantify sensitivity to uncertain parameters (2011, methodology): “The specific formulae used to derive the main effect and interactions can be found in Oakley and O’Hagan(2004).”