Empirical likelihood test via estimating equations |
| |
Authors: | Minqiang Li |
| |
Institution: | a Bloomberg LP, 731 Lexington Avenue, New York, NY 10022, United States b School of Mathematics, Georgia Institute of Technology, Atlanta, GA 30332-0160, United States |
| |
Abstract: | It has been a long history for testing whether the underlying distribution belongs to a particular one or a parametric class of distributions. In this paper, we propose some empirical likelihood ratio tests via estimating equations. The proposed new tests allow one to add more relevant constraints so as to improve the powers. A simulation study shows the effectiveness of the new tests. The new method is then used to test employer size and market value distributions of US firms. |
| |
Keywords: | Empirical likelihood method Estimating equations Goodness-of-fit tests |
本文献已被 ScienceDirect 等数据库收录! |
|