PLS情绪指数对中国股市风险收益关系的影响研究  被引量:3

Impact of PLS Sentiment Index on Relationship between Risk and Return of Chinese Stock Market

在线阅读下载全文

作  者:刘司航 黄创霞 陈宪[1] 文凤华[1] Si-hang LIU Chuang-xia HUANG Xian CHEN Feng-hua WEN(Business School, Central South University, Changsha, Hunan 410083, China School of mathematics and statistics ,Changsha University of Science and Technology ,Changsha, Hunan 410114 ,China)

机构地区:[1]中南大学商学院,湖南长沙410083 [2]长沙理工大学数学与统计学院,湖南长沙410114

出  处:《经济数学》2017年第3期88-95,共8页Journal of Quantitative Economics

基  金:国家自然科学基金(71471020);湖南省自科基金(2016JJ1001);湖南省教育厅重点项目(15A003)

摘  要:从行为金融学角度研究投资者情绪对中国股市风险收益关系的影响,或有助于更好的解释风险收益关系.采用偏最小二乘法(PLS)构建新的投资者情绪综合指数,同时在对风险的度量中运用个股平均相关性代替总体方差来度量市场风险.研究结果表明PLS情绪指数比常用的主成分分析法所构建的情绪指数及单个情绪代理变量能更好的解释股市收益;平均相关性比市场波动更适合作为市场风险的度量指标;投资者情绪对风险收益关系有显著影响,其中在低情绪期风险和收益之间的相关性不显著,而高情绪期风险和收益之间呈现显著的负相关关系.由实证结果可知中国股市投资者存在非理性行为,应从行为金融的角度去考虑资产定价,同时对各指标的准确度量更有利于完善行为资产定价理论.From the perspective of behavioral finance,studying the impact of investor sentiment on the risk return rela- tionship of China stock market may help to better explain the relationship between risk and return.With constructing a new composite sentiment index by the partial least squares(PLS) method and using average correlation to measure risk,it turns out that the PLS sentiment index performs better than other indexes, average correlation is more suitable for measuring market risk,and there is no significant correlation between risk and return during low sentiment, but during high emotional period it shows significant correlation between risk and return.The empirical results show that there exists irrational behavior in Chinese stock market, it is better to consider asset pricing from the perspective of behavioral finance, and the accurate measurement of each index is helpful to refine the behavioral asset pricing theory.

关 键 词:金融市场 风险收益关系 偏最小二乘法 投资者情绪 

分 类 号:F832.5[经济管理—金融学]

 

参考文献:

正在载入数据...

 

二级参考文献:

正在载入数据...

 

耦合文献:

正在载入数据...

 

引证文献:

正在载入数据...

 

二级引证文献:

正在载入数据...

 

同被引文献:

正在载入数据...

 

相关期刊文献:

正在载入数据...

相关的主题
相关的作者对象
相关的机构对象