Dropping variables versus use of proxy variables in linear regression |
| |
| Affiliation: | 1. Department of Statistics, University of Dortmund, 44221 Dortmund, Germany;2. Department of Economics, University of Hamburg, Hamburg, Germany;1. Department of Neurology, Sixth Medical Center of Chinese PLA General Hospital, Beijing, China;2. Department of Clinical Neuroscience, Karolinska Institute, Stockholm, Sweden;3. Department of Neurology, 903RD Hospital of PLA, Hangzhou, China;4. Department of Medicine, Beijing Northern Hospital of China North Industries Group Corporation, Beijing, China;1. Department of Biostatistics and Bioinformatics, Duke University School of Medicine, Durham, NC 27705, United States;2. Department of Biostatistics, University of Michigan, Ann Arbor, MI 48109, United States;1. Theoretical Physics Department, Kursk State University, Radishcheva st., 33, Kursk 305000, Russia;2. Institute of Physics, Humboldt-University at Berlin, Newtonstr.15, 12489, Berlin, Germany |
| |
| Abstract: | In this paper we investigate under which conditions it is preferable to use proxies or to omit variables from the linear regression model with respect to the matrix mean square error criterion. Furthermore, some attention is paid to the admissibility of the proxies-based least squares estimator. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
