Bayesian data analysis: Difference between revisions
Jump to navigation
Jump to search
No edit summary |
No edit summary |
||
| Line 1: | Line 1: | ||
The goal of Bayesian or integrated data analysis is to combine the information from a set of diagnostics providing complementary information in order to recover the best possible reconstruction of the actual state of the system subjected to measurement. | The goal of Bayesian or integrated data analysis is to combine the information from a set of diagnostics providing complementary information in order to recover the best possible reconstruction of the actual state of the system subjected to measurement. | ||
<ref>[http://link.aip.org/link/?RSINAK/75/4237/1 R. Fischer, A. Dinklage, ''Integrated data analysis of fusion diagnostics by means of the Bayesian probability theory'', Rev. Sci. Instrum. '''75''' (2004) 4237]</ref><ref>[http://dx.doi.org/10.1109/WISP.2007.4447579 J. Svensson, A. Werner, ''Large Scale Bayesian Data Analysis for Nuclear Fusion Experiments'', IEEE International Symposium on Intelligent Signal Processing (2007) 1]</ref> | <ref>[http://link.aip.org/link/?RSINAK/75/4237/1 R. Fischer, A. Dinklage, ''Integrated data analysis of fusion diagnostics by means of the Bayesian probability theory'', Rev. Sci. Instrum. '''75''' (2004) 4237]</ref><ref>[http://dx.doi.org/10.1109/WISP.2007.4447579 J. Svensson, A. Werner, ''Large Scale Bayesian Data Analysis for Nuclear Fusion Experiments'', IEEE International Symposium on Intelligent Signal Processing (2007) 1]</ref> | ||
Like [[Function parametrization]], this technique requires having a model to predict the measurement readings for any given state of the physical system; however, the handling of error propagation is more sophisticated with the Bayesian method, and additionally, it provides a systematic way to include prior knowledge into the analysis. | |||
== References == | == References == | ||
<references /> | <references /> | ||
Revision as of 16:42, 9 February 2010
The goal of Bayesian or integrated data analysis is to combine the information from a set of diagnostics providing complementary information in order to recover the best possible reconstruction of the actual state of the system subjected to measurement. [1][2] Like Function parametrization, this technique requires having a model to predict the measurement readings for any given state of the physical system; however, the handling of error propagation is more sophisticated with the Bayesian method, and additionally, it provides a systematic way to include prior knowledge into the analysis.
References
- ↑ R. Fischer, A. Dinklage, Integrated data analysis of fusion diagnostics by means of the Bayesian probability theory, Rev. Sci. Instrum. 75 (2004) 4237
- ↑ J. Svensson, A. Werner, Large Scale Bayesian Data Analysis for Nuclear Fusion Experiments, IEEE International Symposium on Intelligent Signal Processing (2007) 1