In this paper, we consider semiparametric efficient inferences in the generalised partially linear models. A novel bias-corrected estimating procedure and a bias-corrected empirical log-likelihood ratio are developed, respectively, for point estimation and confidence regions for parameters of interest. Under mild conditions, the resulting likelihood ratio is shown to be standard chi-squared distributed asymptotically. Moreover, it is noteworthy that the range of bandwidth in this paper covers the optimal bandwidth due to the implementation of a new bias-corrected technique. Therefore, no undersmoothing is needed here for guaranteeing the asymptotically standard chi-squared distribution of the proposed statistic. Simulation study and real application are also provided in order to illustrate the performance of resulting procedure.

中文翻译：

---

广义部分线性模型的半参数有效推理

在本文中，我们考虑了广义部分线性模型中的半参数有效推理。分别针对感兴趣参数的点估计和置信区域开发了一种新颖的偏差校正估计程序和偏差校正经验对数似然比。在温和条件下，所得似然比显示为标准卡方渐近分布。此外，值得注意的是，由于采用了一种新的偏置校正技术，本文中的带宽范围涵盖了最佳带宽。因此，这里不需要欠平滑来保证所提议的统计量的渐近标准卡方分布。还提供了模拟研究和实际应用，以说明所得程序的性能。