Research On The Structure Of Chinese And American Stock Markets Based On Factor Model Analysis

In the globalized international market,multinational market relations have become the focus of current attention.The shock of events will have a non-negligible impact on the market.China and the United States are currently the two largest economies.The two countries’ market relationship has attracted close attention from all parties.The China-United States trade war is the most significant event in the trade history of the two countries in recent years,and it has had a non-negligible impact on the relationship between the two markets.This article studies how this trade war affects the co-movement between the U.S.stock market and the Chinese stock market,as well as changes in the internal structure of the markets.We focus on the factor structure of stock returns,consider the fluctuation of eigenvalues of the covariance matrix in factor models,and propose a new method to test the model structure.According to the characteristics of the eigenvalues,variables of unknown distributions are transformed into statistics of a known distribution through a randomization method.The built test statistic is used to check for structural breaks in factor models,including changes in factor loadings and increases in the number of factors.This paper examines the factor structure of stock returns in China and the United States from January 1,2017,to December 31,2019.The result suggests that its structure has changed.Then we use a factor model with factors of different strengths to fit daily stock returns.The estimated factors and their corresponding loading matrices are found to vary across periods.In both the pre-trade war period and the trade war period,there are two common factors.Empirical analysis shows that each of the two common factors dominates a market before the trade war.In the trade war period,however,two common factors drive the stock returns in both markets simultaneously:one common factor drives both markets in the same direction,while the other has an opposite effect on the two markets.This research interprets this change from the perspective of a theoretical model,revealing the trade war pattern caused by mixed pricing factors.To further illustrate the structural changes during the trade war period,we use a narrative approach to connect the extreme values of common factors with market-related news reports.By matching with news,the first factor is almost exclusively related to trade,while the second is related to macro information.These results suggest that trade policy shapes the factor structure between the Chinese and American stock markets after the trade war unfolds.