Testing Serial Correlation in Semiparametric Varying-Coefficient Partially Linear Models |
| |
Authors: | Xuemei Hu Zhizhong Wang Feng Liu |
| |
Institution: | 1. Mathematics and Statistics College, ChongQing Technology and Business University , ChongQing, China huxuem@163.com;3. School of Mathematics and Computing Technology, Central South University , ChangSha, China;4. School of Mathematics and Physics, ChongQing Institute of Technology , ChongQing, China |
| |
Abstract: | We propose two test statistics for testing serial correlation in semiparametric varying-coefficient partially linear models. The proposed test statistics are not only for testing zero first-order serial correlation, but also for testing higher-order serial correlations. Under the null hypothesis of no serial correlation, the test statistics are shown to have asymptotic normal or chi-square distributions. By using R, some Monte Carlo experiments are conducted to examine the finite sample performances of the proposed tests. Simulation results show that the estimated size and power of the proposed tests behave well. |
| |
Keywords: | Empirical likelihood Semiparametric varying-coefficient partially linear model Serial correlation |
|
|