Rmt Analysis Of China’S Shanghai Stock Exchange

Alexander Adams

School Name

Governor's School for Science and Math

Grade Level

12th Grade

Presentation Topic

Consumer Science

Presentation Type

Mentored

Mentor

Mentor: Dr. Lim; Department of Physics, Korean Advanced Institute for Science and Technology

Written Paper Award

1st Place

Abstract

We analyzed the structure of cross-correlation in China’s Shanghai Stock Exchange by examining daily price changes of nearly 1000 stocks for the time period between January 1, 2005 and July 15, 2015. We determined characteristics in the Chinese stock market during times of crisis by examining the 2008 crash and the 2015 crash. By determining the probability distribution of yearly cross-correlation matrices, we ascertained that during times of crisis, stocks become highly correlated with one another. We also calculated deviating eigenvalues for four year time periods with a two year sliding window in order to find the magnitude of these correlations. Recognizing that the market wide effect clouds true correlations, we first calculated that China has a large market wide effect through inverse participation ratios, and then removed the effect through regression. After removing the market wide effect, we constructed network analysis diagrams for time periods of four years with a two year sliding window to show how different business sectors interact with each other before, during, and after times of crisis. Because there were fewer correlations in the Shanghai Stock Exchange during the 2015 crash, we concluded that the recent downturn is not as severe as the 2008 crash.

Location

Owens 102

Start Date

4-16-2016 8:30 AM

COinS
 
Apr 16th, 8:30 AM

Rmt Analysis Of China’S Shanghai Stock Exchange

Owens 102

We analyzed the structure of cross-correlation in China’s Shanghai Stock Exchange by examining daily price changes of nearly 1000 stocks for the time period between January 1, 2005 and July 15, 2015. We determined characteristics in the Chinese stock market during times of crisis by examining the 2008 crash and the 2015 crash. By determining the probability distribution of yearly cross-correlation matrices, we ascertained that during times of crisis, stocks become highly correlated with one another. We also calculated deviating eigenvalues for four year time periods with a two year sliding window in order to find the magnitude of these correlations. Recognizing that the market wide effect clouds true correlations, we first calculated that China has a large market wide effect through inverse participation ratios, and then removed the effect through regression. After removing the market wide effect, we constructed network analysis diagrams for time periods of four years with a two year sliding window to show how different business sectors interact with each other before, during, and after times of crisis. Because there were fewer correlations in the Shanghai Stock Exchange during the 2015 crash, we concluded that the recent downturn is not as severe as the 2008 crash.