| Author: | Benjamin Kedem, Victor De Oliveira, Michael Sverchkov | ISBN: | 9789813200203 |
| Publisher: | World Scientific Publishing Company | Publication: | January 24, 2017 |
| Imprint: | WSPC | Language: | English |
| Author: | Benjamin Kedem, Victor De Oliveira, Michael Sverchkov |
| ISBN: | 9789813200203 |
| Publisher: | World Scientific Publishing Company |
| Publication: | January 24, 2017 |
| Imprint: | WSPC |
| Language: | English |
This book comes up with estimates or decisions based on multiple data sources as opposed to more narrowly defined estimates or decisions based on single data sources. And as the world is awash with data obtained from numerous and varied processes, there is a need for appropriate statistical methods which in general produce improved inference by multiple data sources.
The book contains numerous examples useful to practitioners from genomics. Topics range from sensors (radars), to small area estimation of body mass, to the estimation of small tail probabilities, to predictive distributions in time series analysis.
Contents:
- Introduction
- Weighted Systems of Distributions
- Multivariate Extension
- Some Asymptotic Results
- Out of Sample Fusion
- Bayesian Weighted Systems
- Small Area Estimation
Readership: Graduate students, researchers, practitioners of statistics, engineers, scientists.
Key Features:
- A novel idea of "repeated out of sample fusion" applied in the estimation of very small tail probabilities using only moderately large samples. The idea is to fuse real and artificial data to obtain improved estimates of small tail probabilities
- Improved kernel density estimates, univariate as well as multivariate, as compared with traditional kernel density estimates
- A new Bayesian extension of the density ratio model
This book comes up with estimates or decisions based on multiple data sources as opposed to more narrowly defined estimates or decisions based on single data sources. And as the world is awash with data obtained from numerous and varied processes, there is a need for appropriate statistical methods which in general produce improved inference by multiple data sources.
The book contains numerous examples useful to practitioners from genomics. Topics range from sensors (radars), to small area estimation of body mass, to the estimation of small tail probabilities, to predictive distributions in time series analysis.
Contents:
- Introduction
- Weighted Systems of Distributions
- Multivariate Extension
- Some Asymptotic Results
- Out of Sample Fusion
- Bayesian Weighted Systems
- Small Area Estimation
Readership: Graduate students, researchers, practitioners of statistics, engineers, scientists.
Key Features:
- A novel idea of "repeated out of sample fusion" applied in the estimation of very small tail probabilities using only moderately large samples. The idea is to fuse real and artificial data to obtain improved estimates of small tail probabilities
- Improved kernel density estimates, univariate as well as multivariate, as compared with traditional kernel density estimates
- A new Bayesian extension of the density ratio model
