• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Essays in the limits of experiments approach to econometrics.
【24h】

Essays in the limits of experiments approach to econometrics.

机译：计量经济学中实验方法的局限性。

获取原文
获取原文并翻译 | 示例
页面导航
  • 摘要
  • 著录项
  • 相似文献
  • 相关主题

摘要

This collection of essays is concerned with the "limits of experiments" approach to asymptotic theory and its particular application to problems in econometric theory. The first chapter will provide a brief introduction to the "limits of experiments" approach. We will focus on the parts of the theory that are most relevant to the economic applications considered later.;In the second chapter we consider inference procedures on the coefficient on the endogenous regressor in a linear instrumental variables model with a single endogenous regressor, nonrandom exogenous regressors and instruments, and i.i.d. errors whose distribution is unknown. It is shown that under mild smoothness conditions on the error distribution the experiment is locally asymptotically normal (LAN) and, if the model contains an intercept, that adaptation is possible. Consequently, it is possible to develop tests which are nearly efficient (in the sense of [6]) when identification is weak and consistent and asymptotically optimal when identification is strong. In addition, an estimator is presented which can be used in the usual way to construct valid (indeed, optimal) confidence intervals when identification is strong. The estimator is asymptotically efficient under strong identification whether or not the errors are normal.;In the third chapter we consider point and interval estimation of the autoregressive parameter in a nearly-integrated first-order autoregression. Under a local-to-unity parameterization, we exploit the locally asymptotically quadratic structure (LAQ) of the model to construct optimal conditional procedures based on the Gaussian sufficient statistics. These procedures are asymptotically equivalent to procedures which condition on the final observation of the series which is relevant to the problem of forecasting in these models. They are optimal in terms of concentration around the true parameter value within a class of conditional estimators. Additionally, the proposed estimators minimize expected loss across a wide range of loss functions. We also generalize the method for models with a nonzero mean and for higher-order autoregressions.
机译：论文集涉及渐进理论的“实验极限”方法及其在计量经济学理论中的特殊应用。第一章将简要介绍“实验限制”方法。我们将集中讨论与稍后考虑的经济应用最相关的理论部分；在第二章中，我们考虑具有单个内生回归变量，非随机外生回归变量的线性工具变量模型中内生回归变量的系数的推理过程。回归器和工具以及iid分布未知的错误。结果表明，在温和的平滑度条件下，误差分布上的实验是局部渐近正态（LAN）的，并且，如果模型包含截距，则可以进行自适应。因此，有可能开发出在识别能力较弱时几乎有效的测试（从[6]的意义上来说），并且在识别能力较强时则渐近最优。另外，提出了一种估计器，当识别力强时，该估计器可以以通常的方式使用以构造有效（实际上是最佳）置信区间。在误差是否正常的强识别下，估计器是渐近有效的。在第三章中，我们考虑了在近似积分的一阶自回归中自回归参数的点和区间估计。在局部到统一的参数化下，我们利用模型的局部渐近二次结构（LAQ），基于高斯充分统计量构造最佳条件程序。这些过程在渐近性上等同于以该系列的最终观测为条件的过程，该序列与这些模型中的预测问题有关。就一类条件估计器中真实参数值附近的集中而言，它们是最佳的。此外，建议的估算器可将各种损失函数中的预期损失降至最低。我们还将泛化该方法用于均值非零的模型和高阶自回归。

著录项

  • 作者

    Crump, Richard Kingsley.;

  • 作者单位

    University of California, Berkeley.;

  • 授予单位 University of California, Berkeley.;
  • 学科 Economics General.;Economics Theory.
  • 学位 Ph.D.
  • 年度 2009
  • 页码 134 p.
  • 总页数 134
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类
  • 关键词

  • 入库时间 2022-08-17 11:38:25

相似文献

  • 外文文献
  • 中文文献
  • 专利
获取原文

客服邮箱：kefu@zhangqiaokeyan.com

京公网安备：11010802029741号 ICP备案号：京ICP备15016152号-6 六维联合信息科技 (北京) 有限公司©版权所有

  • 客服微信

  • 服务号