• 主题
高级搜索  >
历史搜索 清空历史
首页> 外文学位 >Information content in stock market technical patterns: A spline regression approach.
【24h】

Information content in stock market technical patterns: A spline regression approach.

机译：股市技术模式中的信息内容：样条回归方法。

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

Despite its high popularity among market practitioners, technical analysis has been largely ignored by the academic community on the basis of the efficient markets hypothesis. However, recent evidence on predictability of stock returns from past returns has led many economists to reinterpret the notion of informational efficiency, which, in turn, has sparked interest in direct testing of technical analysis.; One of the main problems in testing technical analysis is the highly subjective nature of some technical methods—often times, predictions are based on visual chart patterns that can not be easily expressed using algebraic methods. Recently, it has been suggested that smoothing estimators are particularly well-suited for the task of visual pattern recognition. It has also been demonstrated that a procedure based on nonparametric kernel regression can be used effectively for identification of visual technical patterns. However, a kernel-based pattern identification procedure has a number of shortcomings that directly affect the quality of pattern recognition. One of the most serious issues is the problem of bandwidth selection. Typically, kernel regression procedures are used in conjunction with data-driven methods for optimal bandwidth selection. The previous research has demonstrated that such methods fail to produce satisfactory results in the context of visual technical patterns.; The focus of this project is to test informativeness of ten popular technical patterns using an alternative approach based on the spline regression methodology. The spline-based pattern identification algorithm effectively bypasses the bandwidth selection problem by directly incorporating the geometry of technical patterns in the regression procedure. The spline regression algorithm was applied to a large number of stocks from 1963 to 1997 to evaluate the efficacy of visual technical patterns. The results of the spline-based analysis suggest that a number of technical patterns do provide valuable investment information.
机译：尽管它在市场从业者中很受欢迎，但基于有效市场假说，技术分析在很大程度上已被学术界所忽略。然而，最近关于股票收益可预测性的证据使许多经济学家重新解释了信息效率的概念，这反过来激发了人们对技术分析直接测试的兴趣。测试技术分析的主要问题之一是某些技术方法的高度主观性-通常，预测是基于视觉图表模式进行的，这些模式无法使用代数方法轻松表达。最近，已经提出平滑估计器特别适合于视觉模式识别的任务。还已经证明，基于非参数核回归的过程可以有效地用于视觉技术模式的识别。但是，基于内核的模式识别过程具有许多缺点，这些缺点直接影响模式识别的质量。最严重的问题之一是带宽选择问题。通常，将内核回归过程与数据驱动方法结合使用以实现最佳带宽选择。先前的研究表明，这种方法无法在视觉技术模式的背景下产生令人满意的结果。该项目的重点是使用基于样条回归方法的替代方法来测试十种流行技术模式的信息性。基于样条的模式识别算法通过在回归过程中直接合并技术模式的几何形状，有效地绕过了带宽选择问题。从1963年到1997年，样条回归算法应用于大量股票，以评估视觉技术模式的有效性。基于样条的分析结果表明，许多技术模式确实提供了有价值的投资信息。

著录项

  • 作者

    Markov, Dennis.;

  • 作者单位

    University of Notre Dame.;

  • 授予单位 University of Notre Dame.;
  • 学科 Economics Finance.
  • 学位 Ph.D.
  • 年度 2002
  • 页码 135 p.
  • 总页数 135
  • 原文格式 PDF
  • 正文语种 eng
  • 中图分类 财政、金融;
  • 关键词

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