Title page for etd-0526115-123709


[Back to Results | New Search]

URN etd-0526115-123709
Author FENG-SUNG CHIEN
Author's Email Address No Public.
Statistics This thesis had been viewed 5358 times. Download 0 times.
Department Finance
Year 2015
Semester 1
Degree Master
Type of Document
Language English
Title Macroeconomic Multi-Factor Model
Date of Defense 2015-05-28
Page Count 59
Keyword
  • principal component analysis
  • multi-factor model
  • macroeconomic indicator
  • unit root test
  • factor analysis
  • Abstract The purpose of this paper is to construct a macroeconomic multi-factor risk model based on the listed stock market in Taiwan. The first part is to filter out the effective factors. We collect macroeconomic indicators from Taiwan and the USA and perform a unit root test to make sure that our data are stationary time series. We select the effective indicators according to the criteria in this paper and then use factor analysis and principal component analysis to derive our composite macro factors. The second part is to build the risk model, including estimating the factor exposure, specific return, specific risk and factor return covariance matrix. Finally, we conduct a bias test to evaluate the performance of our model during the out-of-sample period from 2008/01 to 2014/12. Our empirical results show the average R-squared of our model is 22%, which indicates that the macro factors selected using the methodology in this paper can explain part of the variability of stock returns and provide fund managers with macroeconomic viewpoints when doing index tracking or constructing enhanced portfolios.
    Advisory Committee
  • Shyh-Weir Tzang - chair
  • Yih Jeng - co-chair
  • Wei-Che Tsai - advisor
  • Files
  • etd-0526115-123709.pdf
  • Indicate in-campus at 5 year and off-campus access at 5 year.
    Date of Submission 2016-02-17

    [Back to Results | New Search]


    Browse | Search All Available ETDs

    If you have more questions or technical problems, please contact eThesys