Fitting generalized linear models and their nonlinear extensions with least squares calculations |
| |
| Affiliation: | 1. Domain of Materials Science and Engineering, Graduate School of Science and Engineering, Ibaraki University, Hitachi, Ibaraki, Japan;2. Divisions of Neutron Beamline and Research, Frontier Research Center for Applied Atomic Sciences, Tokai, Ibaraki, Japan;3. Institute for Integrated Radiation and Nuclear Science, Kyoto University, Kumatori, Osaka, Japan;4. Institute for Quantum Life Science, National Institutes for Quantum and Radiological Science and Technology, Tokai, Ibaraki, Japan |
| |
| Abstract: | A class of maximum likelihood algorithms called NRL algorithms that can be implemented with a sequence of least squares calculations is developed. When applied to generalized linear models and their nonlinear extensions, this class includes several algorithms that have been previously proposed. Properties of the algorithms are examined both in the initial iterations and also near the maximum likelihood estimate; different types of algorithm often perform best in these two situations. A strategy for switching between two such NRL algorithms is presented. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
