Frontiers in Business, Economics and Management 
ISSN: 2766-824X | Vol. 7, No. 2, 2023 

 

26 

A	Preliminary	Empirical	Study	on	the	Influencing	
Factors	of	China's	Economic	Growth	
Yilang Luo1, *, Wenbo Li2 

1School of Finance, Anhui University of Finance and Economics, Bengbu, China 
2School of Economics and Resource Management, Beijing Normal University, Beijing, China 

 

Abstract: Many countries or regions around the world have seen their economic growth slow in recent years due to the impact 
of the COVID-19 pandemic. It is of great significance to the world that China's economy is the first to recover from the impact 
of COVID-19. This paper selects the data of various economic development indicators of China from 2002 to 2021, establishes 
the multiple linear regression model of economic growth, and makes a preliminary analysis of the influencing factors of China's 
economic growth. This paper explores the influence of export, consumption and investment on China's economic growth. Finally, 
it puts forward relevant suggestions for further high-quality sustainable development of China's economy. 

Keywords: COVID-19, Economic growth, Influencing factors, High-quality development. 
 

1. Introduction 
In recent years, the COVID-19 pandemic has brought many 

risks and challenges to the global economy. The global 
economy continues to slow down and the economic 
environment is complex and volatile. As the second largest 
economy in the world, the epidemic continues to occur 
frequently in China, and both the demand side and the supply 
side of the domestic economy have suffered significant 
negative impacts, and the economy is facing considerable 
downward pressure (Chen and Guo, 2020). In order to 
stabilize the domestic economy as soon as possible and 
further stabilize and develop the economy in a good way, it is 
of great practical significance to make an empirical analysis 
on the influencing factors of our economic growth. This paper 
selects the "three carriages" which promote the economic 
growth in the macroeconomic theory, namely export, 
consumption and investment, analyzes which indicator plays 
a more significant role in the process of our country's high-
quality economic growth, and gives the focus on the course 
of our economic development in the future. 

2. Literature Review 
China is the first major economy to recover after the 

economic slowdown caused by the COVID-19 (Wang and 
Zhang, 2021). At present, a number of scholars have done 
research on how to promote China's economic growth. Wang 
(2022) points out that for a country, national consumption can 
promote domestic demand, thus enhancing internal impetus, 
stimulating consumption and ultimately achieving the 
purpose of economic growth. However, at the present stage, 
the research on our economic growth mainly focuses on 
factors such as material, system and model, while the 
attention on national consumption is seriously insufficient. 
Fan (2022) held the view that the international economic and 
trade field is constantly expanding, and China's foreign trade 
volume is also growing. In the context of the continuous 
development of the global COVID-19 pandemic, the 
international market is complex and changeable, and Chinese 
foreign trade enterprises will face huge development 
opportunities and challenges. According to the current trend 

of international economic and trade development, our country 
should focus on supporting advantageous industries, give full 
play to industrial advantage, enhance brand influence and 
international reputation of local international transnational 
corporations, increase dynamics of foreign trade and 
investment to combine them with national development 
strategy, effectively safeguard our country's economic 
interests in the international market and raise our international 
position in foreign trade. What’s more, Internet Technologies 
have broken the boundaries of traditional geographical space, 
which has helped accelerate the decline in energy 
consumption intensity through economic growth, research 
and development investment, human capital, financial 
development and industrial structure upgrading (Ren et al., 
2021). 

3. Research Design 

3.1. Index selection 
This study refers to many scholars’ research on economic 

growth, and makes a preliminary study on the factors that 
promote China’s economic growth (Ren et al., 2014; Liu et 
al., 2021; Zhao et al., 2022). 

3.1.1. Gross domestic product 
Gross domestic product (GDP) is one of the most important 

indicators to measure a region's economic situation. Gross 
Domestic Product (GDP) is the final result of production 
activities of all resident units of a country in a specific period. 
It is the core index to measure the economic development of 
a country. In the course of my development in recent decades, 
the GDP growth rate has been among the highest in the world. 
In this paper, China's GDP from 2002 to 2021 is selected as 
one of the main research indicators to better study economic 
development. 

3.1.2. Total exports 
Total exports usually refer to the total value of a country's 

foreign trade exports. To be specific, the total amount of 
export refers to the total value of a country's exports to foreign 
countries in a certain period, which is called the total amount 
of export. This paper studies the total export volume within 
the scope of China. By taking the total export volume as one 
of the research indicators, we can specifically explore the role 



 

27 

of export and international trade in economic development 
from 2002 to 2021. Generally, the higher the total export 
volume, the more likely to have a trade surplus, that is, in 
international trade, the more easily funds flow to our side, so 
generally, the higher the total export volume, the more active 
the economic development, the higher the level of economic 
development. 

3.1.3. Household consumption level 
National consumption is directly related to the living 

standard and the scale of domestic demand. If the 
consumption level of residents in a region or country is high, 
the country or region will have a higher degree of affluence. 
On the economic level, the country's economic development 
is relatively good. On the other hand, a high level of consumer 
consumption means a higher income, which means that the 
enterprises in the country have better earnings and the 
national economic development is stable. Among all kinds of 
statistical data and data, residents' consumption level is the 
most direct data showing domestic consumption demand, as 
well as one of the important indicators to study changes in the 
retail market and reflect economic and economic degree. In 
this study, the consumption level of Chinese residents is 
selected. Through regression analysis, the relationship 
between it and economic growth can be studied to see its 
specific role in economic growth. Generally speaking, the 
higher the average consumption level, the more prosperous 
the economy, and the higher the living standard and happiness 
of the people. 

3.1.4. Total social investment in fixed assets 
Social investment in fixed assets is a comprehensive index 

reflecting the scale, speed, proportion and direction of 

investment in fixed assets. It represents the workload of 
construction and purchase of fixed assets in monetary form. 
In this paper, China's social fixed asset investment in the past 
20 years is selected as one of the research indicators, focusing 
on the driving effect of investment on regional economy to 
provide directional guidance for economic development. 

3.2. Data sources 
In this study, various kinds of economic indicators in China 

from 2022 to 2021 are selected as sample size, and the data 
used are from China Statistical Yearbook produced by 
National Bureau of Statistics of China. 

3.3. Variable selection 
3.3.1. Explained variable 

In this study, GDP from 2002 to 2021 is selected as 
explanatory variable Y. 

3.3.2. Explanatory variables 
According to the expression of the above index selection, 

the following indexes are selected as explanatory variables: 
total export (X1), resident consumption level (X2), total 
social fixed asset investment (X3), μ is the random error term. 

4. Model Construction and Test 

4.1. Correlation chart and trend chart analysis 
The trend chart for each variable is as shown in Figure 1. 

From Figure 1, we can see that each explanatory variable 
changes in the same direction as the explained variable, and 
the gap becomes larger as the time goes by. 

 

 
Figure 1. Trend chart of explanatory variables and explained variables 

 

 
Figure 2. Correlation graph between each explanatory variable and the explained variable 

 



 

28 

 
The correlation graph between each explanatory variable 

X1, X2, X3 and the explained variable Y is shown in Fig. 2, 
and the results show that there is a positive and high linear 
correlation between each explanatory variable and the 
explained variable. Therefore, the linear regression model is 
selected in this paper, and the model is preliminarily defined 
as follows: 

𝑌 𝛽 𝛽 𝑋 𝛽 𝑋 𝛽 𝑋 𝜇. 

4.2. OLS parameter estimation 
The least squares estimation of GDP and other index data 

in Table 1 is carried out in this paper. The parameter 
estimation results are shown in Table 3. 

 
Table 3. Results of multiple regression estimation 

Variable Y 
X1 0.8995*** 
X2 32.8191*** 
X3 -0.0133 
R2 0.9988 

Prob(F-statistic) 0.0000 
N 20 

 
Note: Standard errors are in parentheses. *, **, *** indicate 

significant at the statistical level of 10%, 5%, and 1% level, 
respectively. 

 
According to Table 3, the results estimated by the multiple 

linear regression model can be obtained as follows: 
𝑌 45059.31 0.8995𝑋 32.8191𝑋 0.0133𝑋 . 

𝑠 11249.25    0.2078    2.2101    0.1295  
𝑡 4.0055    4.3296    14.8497    0.1026  
𝑅 0.9988   𝑅 0.9986   𝐹 4599.533   𝐷. 𝑊.

0.7889   𝑛 20 
According to the results of the model estimation, the 

decidable coefficient 𝑅 0.9988  and the modified 
decidable coefficient 𝑅 0.9986, the model as a whole fits 
the sample well; when the significance level 𝛼 0.05, the 
value of the F-statistic of the model is 4599.533, which is 
much larger than its critical value, and the regression equation 
is significant. That is, the total exports of China, the level of 
consumption of the population, and the amount of investment 
in fixed assets of the whole society have a significant impact 
on China's gross domestic product, i.e., economic growth; 
however, the parameters of the explanatory variable 𝑋  are 
negative and cannot pass the economic significance test, and 
when the significance level 𝛼 0.05, the absolute value of 
the t-statistic value of the explanatory variable 𝑋  is less than 
2 and the p-value is 0.9195 0.05 . The significance test 
cannot be passed. Therefore, the established model needs to 
be revised. 

4.3. Model test and correction 
4.3.1. Test and correction of multicollinearity 

The test results of correlation coefficient are shown in 
Table 2. It can be seen that there is a high linear correlation 
among all explanatory variables, and the minimum value is 
0.9379, which is bigger than 0.8. This indicates that the model 
has severe multicollinearity. 

 
Table 2. Correlation coefficient matrix table 

Correlation Y X1 X2 X3 
Y 1 0.9519 0.9984 0.9914 

X1 0.9519 1 0.9379 0.9574 
X2 0.9984 0.9379 1 0.9892 
X3 0.9914 0.9574 0.9892 1 

 
To further verify, test the variance inflation factor of the 

model, as shown in Table 3. 
 

Table 3. VIF calculation results 
Variable Coefficient 

Variance 
Uncentered 

VIF 
Centered 

VIF 
X1 0.0432 91.6748 12.5958 
X2 4.8845 197.2648 48.8522 
X3 0.0168 255.0254 70.5662 

 
Experience shows that if the variance inflation factor is 

greater than or equal to 10, there is severe multicollinearity 
between this explanatory variable and other explanatory 
variables. It can be seen from Table 3 that the variance 
inflation factors of the three explanatory variables are 
12.5958, 48.8522 and 70.5662 respectively, all of which are 
much higher than 10, indicating the existence of serious 
multicollinearity. In this paper, stepwise regression is used to 
correct the multicollinearity among explanatory variables in 
the model. 

As can be seen from Table 2, the simple correlation 
coefficient between residents' consumption level (X2) and the 
explained variable GDP (Y) is the highest, indicating that 
residents' consumption level is the most important factor 
affecting GDP. Therefore, a basic unary regression model is 
established with X2 as the explanatory variable, and then the 
remaining explanatory variables are introduced into the unary 
regression equation respectively. The results of stepwise 
regression analysis are shown in Table 5. 

 
Table 5. Stepwise regression results 

Variable Y 
X1 0.8871*** 
X2 32.6125*** 
R2 0.9988 

Prob(F-statistic) 0.0000 
N 20 

 
Note: Standard errors are in parentheses. *, **, *** indicate 

significant at the statistical level of 10%, 5%, and 1% level, 
respectively. 

 
According to the results obtained after stepwise regression, 

when the significance level α=0.05, based on the unary 
regression equation of X2, explanatory variable X3 cannot 
pass the test. Therefore, variable X3 is removed and the final 
equation obtained by stepwise regression analysis is: 



 

29 

𝑌 44316.16 32.6125𝑋 0.8871𝑋 . 
𝑠 8353.441    0.8845    0.1637  
𝑡 5.3051    36.8723    5.4175  

𝑅 0.9988   𝑅 0.9987   𝐹 7325.679   𝐷. 𝑊.
0.7769   𝑛 20 

The model is improved after modification and the 
multicollinearity of the model can be eliminated. The 
coefficient of determinability and the adjusted coefficient of 
determinability are both greater than 0.99, indicating that the 
model has a high degree of fitting to the samples and has 
passed the test of economic significance. Moreover, F statistic 
is 7352.679, and its adjoint probability is close to 0, indicating 

that the overall linear relationship of the model is significant, 
indicating that each explanatory variable has a significant 
impact on the explained variable gross domestic product Y. 

4.3.2. Test and correction of autocorrelation 
We use DW test to check whether the model has 

autocorrelation. Because n=20, k=2, when the significance 
level is 0.05, dL=1.100,dU=1.1537, and DW=0.7769<dL can 
be obtained from the table. Therefore, it is preliminatively 
judged that there may be a first-order positive correlation in 
the model. In order to further verify the existence of high-
order autocorrelation in the model, the partial correlation 
coefficient test method was used to test the model. 

 

 
Figure 3. Partial correlation coefficient test results 

 
It can be seen from the partial correlation coefficient 

histogram in Fig. 3 that the straight squares in the first phase 
exceed the dashed line and the P-value is less than 0.05, so it 
can be determined that the model has first-order 
autocorrelation. 

Since the above tests show that there is a first-order 
autocorrelation in the model, it is necessary to apply the 

generalized difference method to add AR(1) to the model for 
correction. We can get the revised model as follows: 

𝑌 36300.89 0.6240𝑋 34.1609𝑋 𝐴𝑅 1
0.7235 . 

𝑅 0.9993   𝐹 7748.450   𝐷. 𝑊. 1.5335 

 

 
Figure 4. Test results of the modified model by partial correlation coefficient method 

 
It can be seen from Fig. 4 that the histogram of partial 

correlation coefficient shows that the straight square in the 
first phase no longer exceeds the dotted line and the P-value 
of Q statistic is also greater than 0.05, so it can be determined 
that the modified model eliminates the first-order 
autocorrelation. 

4.3.3. Test of heteroscedasticity 
In order to verify whether the modified model still has 

heteroscedasticity, the residual diagram of the model is drawn 
as shown in Figure 5. 

 



 

30 

-20,000

-10,000

0

10,000

20,000

0

200,000

400,000

600,000

800,000

1,000,000

1,200,000

2002 2004 2006 2008 2010 2012 2014 2016 2018 2020

Residual
Actual
Fitted

 
Figure 5. Residual trend chart 

 
It can be roughly seen from Fig. 5 that the residuals do not 

gradually increase over time, so there may be no 
heteroscedasticity in the model. For further verification, 
White test and ARCH test were conducted. From the results 
of the White test, it can be known that 𝑛𝑅 11.3891
𝜒  𝑝 𝜒 .  10 18.307 , with a concomitant 
probability of 0.3280 greater than the given 0.05; meanwhile, 
from the results of the ARCH test, it can be known that the 
results showing to a lag of one period, n p  𝑅
2.9697 𝜒  𝑝 𝜒 .  1 3.841. In summary, there is 
no hetero-skedasticity in the model. Through the above series 
of tests, we determined the final model as follows: 

 
𝑌 36300.89 0.6240𝑋 34.1609𝑋 𝐴𝑅 1

0.7235 . 
13662.39    0.1921    1.1247    0.1841  

2.6570    3.2486    30.3747    3.9292  
𝑅 0.9993   𝑅 0.9992   𝐹 7748.450   𝑃 𝐹

0.0000   𝐷. 𝑊. 1.5335 
 

5. Conclusions and Suggestions 
Based on the estimated and revised economic growth 

model, we know that the total export and retail sales of 
consumer goods have a significant influence on the GDP of 
China. In addition, if the least squares estimate of the total 
social fixed assets investment is carried out separately, it is 
found that the total social fixed assets investment also has a 
significant impact on the GDP. Based on the existing research 
and literature, and combined with the results of this study, this 
paper proposes the following policy recommendations on 
how to further promote economic growth and high-quality 
economic development in China. 

5.1. Expanding export trade and driving 
economic growth through international 
trade 

From the conclusion of this paper, export trade can 
effectively drive economic growth. Expanding foreign trade 
further can effectively export all kinds of industrial 
manufactured goods in our country. Our country should 
actively exert its own advantages, expand export trade, while 
improving quantity, further optimize the level of 
manufacturing, output a large number of high-quality 
products, so as to effectively occupy the international market, 
promote the domestic and even the world economic growth 
and high-quality development. 

5.2. Promoting personal consumption and 
promoting economic vitality through 
consumption 

National consumption level is an important factor that 
affects economic growth and embodies economic vitality. If 
we want to promote the high-quality growth of our economy, 
it is indispensable to promote the effective improvement of 
residents' consumption level, so as to promote the economic 
development through consumption. The essence of 
consumption to promote economic development is to make 
the market have more wealth, so as to promote the expansion 
of production, from the scale of the whole society is the 
process of increasing wealth. 

5.3. Further improving infrastructure and 
promoting efficient economic development 

Investment in infrastructure, which allows businesses and 
businesses to operate more efficiently, increases productivity 
and better serves economic goals. If China continues to 
improve the quality of infrastructure construction and 
services, better facilitate production activities and ensure a 
stable and orderly production order, it can optimize the 
economic development model and promote high-quality and 
sustainable economic growth. 

Acknowledgment 
This paper was supported by the National Innovation and 

Entrepreneurship Training Program for Undergraduates in 
China (202210378138) and the Undergraduate Research 
Innovation Fund Project of School of Finance of Anhui 
University of Finance and Economics (JR2022004). 

References 
[1] Chen, S., and Guo, J. 2020. Analysis of the economic impact 

of COVID-19: long-term perspective and short-term response. 
Economic Theory and Management 8, 32-44. (in Chinese) 

[2] Fan, S. 2022. Development trend of international economy and 
trade and strategic choice of China's foreign trade. China 
Business Theory 20, 31-33. (in Chinese) 

[3] Liu, D., Ji, X., and Zhu, L. 2021. Analysis of temporal changes 
and influencing factors of marginal propensity to consume of 
urban and rural residents. Statistics and Decision 37(14), 117-
120. (in Chinese) 

[4] Ren, S., Hao, Y., Xu, L., Wu, H., and Ba, N. 2021. 
Digitalization and energy: How does internet development 



 

31 

affect China's energy consumption? Energy Economics 98, 
105220. 

[5] Ren, S., Yuan, B., Ma, X., and Chen, X. 2014. International 
trade, FDI (foreign direct investment) and embodied CO2 
emissions: a case study of Chinas industrial sectors. China 
Economic Review 28, 123-134. 

[6] Wang, J. 2022. On the relationship between economic growth 
and national consumption. Exhibition Economics 12, 21-23. (in 
Chinese) 

[7] Wang, Q., and Zhang, F. 2021. What does the China’s 
economic recovery after COVID-19 pandemic mean for the 
economic growth and energy consumption of other countries? 
Journal of Cleaner Production 295, 126265. 

[8] Zhao, S., Cao, Y., Feng, C., Guo, K., and Zhang, J. 2022. How 
do heterogeneous R&D investments affect China's green 
productivity: Revisiting the Porter hypothesis. Science of the 
Total Environment 825, 154090.