Paper: arXiv 2501.08668

Authors: Jingchu Zhang

Abstract

This paper mainly utilizes the ARDL model and principal component analysis to investigate the relationship between the volatility of China’s Shanghai Composite Index returns and the variables of exchange rate and domestic and foreign bond yields in an internationally integrated stock market. This paper uses a daily data set for the period from July 1, 2010 to April 30, 2024, in which the dependent variable is the Shanghai Composite Index return, and the main independent variables are the spot exchange rate of the RMB against the US dollar, the 10-year treasury bond yields in China and the United States and their lagged variables, with the effect of the time factor added. Firstly, the development of the stock, foreign exchange and bond markets and the basic theories are reviewed, and then each variable is analyzed by descriptive statistics, the correlation between the independent variables and the dependent variable is expanded theoretically, and the corresponding empirical analyses are briefly introduced, and then the empirical analyses and modeling of the relationship between the independent variables and the dependent variable are carried out on the basis of the theoretical foundations mentioned above with the support of the daily data, and the model conclusions are analyzed economically through a large number of tests, then the model conclusions are analyzed economically. economic analysis of the model conclusions, and finally, the author proposes three suggestions to enhance the stability and return of the Chinese stock market, respectively. Key Words: Chinese Stock Market, Volatility, GARCH, ARDL Model

Complexity vs Empirical Score

  • Math Complexity: 5.0/10
  • Empirical Rigor: 6.0/10 (capped from 6.5: no out-of-sample test; see penalty flags)
  • Quadrant: Holy Grail — high math complexity, high empirical rigor (effective empirical rigor capped from 6.5)

Why this score: The paper uses established econometric models (ARDL, PCA, GARCH) with standard derivations, placing it at moderate math complexity, while the extensive daily dataset, statistical testing, and multi-variable analysis indicate strong empirical rigor suitable for implementation.

Research Flowchart

  flowchart TD
  Start["Research Goal:<br>'Identify Factors Influencing<br>China's Stock Market Volatility'"] --> Data["Data (Daily: Jul 2010 - Apr 2024)<br>- Shanghai Composite Index Returns<br>- RMB/USD Exchange Rate<br>- China & US 10Y Treasury Yields"]
  Data --> Methods["Key Methodology<br>- ARDL Model<br>- Principal Component Analysis<br>- GARCH (Volatility Estimation)"]
  Methods --> Process["Computational Process<br>1. Descriptive Statistics<br>2. Correlation Analysis<br>3. Unit Root Tests<br>4. Long-run & Short-run Modeling"]
  Process --> Outcomes["Key Findings/Outcomes<br>- Established Stock-Bond-FX Nexus<br>- Identified Lagged Variables Impact<br>- Policy Suggestions:<br>  1. Diversify Investment<br>  2. Improve Market Mechanisms<br>  3. Monitor Global Spillovers"]

Evidence Card

What the authors claim, on what data, and who has checked it. Read from the paper's own text by a language model: every quote is verbatim, nothing was re-run. How to read this card

Proposes

The paper proposes using an ARDL model combined with principal component analysis to study the impact of exchange rates and bond yields on Shanghai Composite Index returns.

Source sentence
This paper mainly utilizes the ARDL model and principal component analysis to investigate the relationship between the volatility of China's Shanghai Composite Index returns and the variables of exchange rate and domestic and foreign bond yields

Assumes 2

  • The interrelationships between exchange rate, bond yields and stock return are both negative. model
    Source sentence
    It is also assumed that the interrelationships between these two independent variables and the dependent variable are both negative.
  • The time‑series variables must be stationary for modeling. statistical
    Source sentence
    Since the sample data used in the article are also time series, the ADF test is chosen to ensure the stationarity of the data.

Data

  • Shanghai Composite Index daily returns · National Bureau of Statistics, People's Bank of China, Wind macro public
    2010-07-01 to 2024-04-30 · Shanghai Composite Index
    Source sentence
    In the selection of data, the author chooses the daily data of each variable. First of all, whether it is the daily data of the Shanghai Composite Index or the daily data of the RMB exchange rate, or the daily data of the national bond yields of various countries, all of them can be found directly on the official websi
  • Daily USD‑CNY exchange rate (FXR) · People's Bank of China, Wind Database macro public
    2010-07-01 to 2024-04-30
    Source sentence
    FXR (Foreign Exchange Rate): Daily USD‑RMB exchange rate
  • Daily Chinese Government Bond yield (CNB) · People's Bank of China, Wind Database macro public
    2010-07-01 to 2024-04-30
    Source sentence
    CNB (China Bond Yield) Daily Chinese Government Bond yield
  • Daily US Treasury Bond yield (USB) · Wind Database macro public
    2010-07-01 to 2024-04-30
    Source sentence
    USB (United States Bond Yield): Daily US Treasury Bond yield

Recognised sources: Wind

Costs

Not applicable The paper reports no trading or execution result.

Finds 3

  • The Shanghai Composite Index return is positively correlated with the exchange rate and negatively correlated with Chinese and US treasury bond yields and their lagged variables. statistical
    Source sentence
    The final model shows that the return of China's Shanghai Composite Index is positively correlated with the exchange rate variable, while it is negatively correlated with the treasury bond yields of China and the United States and its own lagged variables
  • Principal component analysis resolves multicollinearity among the explanatory variables. theoretical
    Source sentence
    Empirically, the multicollinearity between variables is resolved by using principal component analysis
  • All variables except the dependent volatility series are non‑stationary in levels but become stationary after first differencing. statistical
    Source sentence
    From the above ADF test results, it can be seen that, except for the dependent variable VOL series itself is stationary, the P-value of all the other variables itse…

Checked by others

No other paper in the archive has been found to support or contradict these findings (compared with 24 related papers). Coverage is partial, so this is neither replication nor refutation.

Code

No repository by the authors found in the paper.

Extracted 2026-11-14 · same card as JSON · A language model chose these items: check the source sentence before relying on one.