Robustness of subset selection procedures |
| |
| Institution: | 1. College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, China;2. State Key Laboratory of Tree Genetics and Breeding, Co-Innovation Center for Sustainable Forestry in Southern China, Key Laboratory of Tree Genetics and Biotechnology of Educational Department of China, Key Laboratory of Tree Genetics and Silvicultural Sciences of Jiangsu Province, College of Information Science and Technology, Nanjing Forestry University, Nanjing 210037, China;3. Institute of Forest Resource Information Techniques, Chinese Academy of Forestry, Beijing 100091, China;1. Key Laboratory for Efficient Utilization of Water Resources in Dryland Areas in Gansu Province, Lanzhou 730070, Gansu, China;2. Dryland Agriculture Institute, Gansu Academy of Agricultural Sciences, Lanzhou 730070, Gansu, China |
| |
| Abstract: | The robustness (and the number of non-best populations selected) of 11 subset selection procedures is investigated by means of simulation experiments. If the underlying distributions differ only in their location parameter, the subset selection procedures are robust for symmetric distributions or distributions with negative skewness. With increasing positive skewness and increasing number of populations the considered parametric procedures fail in robustness slightly. This non-robustness is more serious in the case of unequal variances. Non-parametric subset selection rules show then an increasing non-robustness with increasing sample size. |
| |
| Keywords: | |
| 本文献已被 ScienceDirect 等数据库收录！ |
|
