A new class of asymptotically efficient estimators for moment condition models |
| |
Authors: | Yanqin Fan Matthew Gentry Tong Li |
| |
Institution: | a Department of Economics, Vanderbilt University, VU Station B #351819, 2301 Vanderbilt Place, Nashville, TN 37235-1819, United States |
| |
Abstract: | In this paper, we propose a new class of asymptotically efficient estimators for moment condition models. These estimators share the same higher order bias properties as the generalized empirical likelihood estimators and once bias corrected, have the same higher order efficiency properties as the bias corrected generalized empirical likelihood estimators. Unlike the generalized empirical likelihood estimators, our new estimators are much easier to compute. A simulation study finds that our estimators have better finite sample performance than the two-step GMM, and compare well to several potential alternatives in terms of both computational stability and overall performance. |
| |
Keywords: | |
本文献已被 ScienceDirect 等数据库收录! |
|