- Study topic and purpose
- Dependent and independent variables
- Regression Equation
- The motivation for selecting the topic
- Regression model and the hypotheses to be tested
- Description of the data to be used
- Why simple OLS is not suitable for estimating the model above
- Estimation Results by OLS
- Another method
- Works Cited
Study topic and purpose
This paper aims at investigating the determinants of Foreign Direct Investment in China. The factors that attract FDI in China will be explored. The paper seeks to find out the impacts of Gross Domestic Product, Wages, Imports, and Exports on the Foreign Direct Investment in China. The investigation will be done quantitatively using secondary data.
Dependent and independent variables
Dependent variable
The dependent variable is Foreign Direct Investment that will be denoted by Y for purposes of analysis. This is the variable that is being determined using other variables. The effect that other factors have on this variable is what the study aims to find out.
The independent variable
These are the variables whose effects on the dependent variable are being investigated. Their values are exogenously determined. For this research, the following dependent variables are believed to have some impact on Foreign Direct Investment.
- GDP growth which will be denoted by X1
- Export in China denoted by X2
- Import in China denoted by X3
- Wage IN China which will be denoted by x4 for purpose of this analysis
Regression Equation
The variables named above will be related in the following regression model:
FDI= β0 + β 1 GDP growth + β 2 export + β 3 import + β 4 Wage+ u. However, for purposes of simplicity and ease of analysis, the variables will be denoted by Xi as indicated above. Where i = 1, 2, 3, 4. The model, therefore, is presented as follows:
Y = β0 + β 1 X1 + β 2 X2 + β 3 X3+ β 4 X4 + µ.
The motivation for selecting the topic
This topic was selected for this empirical paper because China is one of the fastest-growing economies in the world. The rate of growth has been of interest by all countries in the world including the developed economies like the US and UK. According to Graham and Wada, “by almost all accounts, foreign direct investment (FDI) in China has been one of the major success stories of the past 10 years” (1).
The trend of the growth of FDI in China has been very high, having a base of less than $19 billion in 1990 to over $300 billion by the end of 1999 and more than that in recent years. Such growth in FDI, with the prevailing level of competition in the world by economies to raise their FDI, is worth investigating. The factor which causes a high level of FDI is an area that is not fully investigated. It is important to investigate the reason for the high level of FDI in China. This is one of the factors that are contributing to the high growth of the country’s economy.
Regression model and the hypotheses to be tested
The regression model that will be investigated is as stated below:
Y = β0 + β 1 X1 + β 2 X2 + β 3 X3+ β 4 X4 + µ. The variables stand as defined earlier with µ denoting the stochastic term or the error term (Rubin 34).
The study seeks to test the following hypotheses:
H0 denotes the null hypothesis while H1 denotes the alternative hypothesis.
H0: β1 = 0, GDP growth (X1) is a significant determinant of FDI (Y) in China
H1: β1 ≠ 0, GDP growth (X1) is not a significant determinant of FDI (Y) in China
H0: β2 = 0, Export (X2) is a significant determinant of FDI (Y) in China
H1: β2 ≠ 0, Export (X2) is not a significant determinant of FDI (Y) in China
H1: β3 ≠ 0, Imports (X3) are not significant determinants of FDI (Y) in China
H1: β3 ≠ 0, Imports (X3) is not a significant determinant of FDI (Y) in China
H1: β4 ≠ 0, Wages (X4) are not significant determinants of FDI (Y) in China
H1: β4 ≠ 0, wages (X4) are not significant determinants of FDI (Y) in China
Description of the data to be used
The data used is of a time series nature. The reason for this is because the topic requires observation of trends in China. The data will be collected from the China bureau of statistics and other sources that contains such data. The data used is for the years 1995 to 2011. The data is time-series data that has been recorded over time.
Why simple OLS is not suitable for estimating the model above
The OLS method makes several assumptions which may lead to inaccurate estimates or estimation of the model. Firstly, the method assumes that the error term has a constant variance which may not be the case. The error term is also assumed to be normally distributed with a mean of zero and constant variance. Since the data used in this empirical work is time-series data, using OLS for estimation assumes that the error terms in different periods are not correlated. They are independent of each other. The other assumption is that the error term is not correlated with the independent variables. All these assumptions may not always hold (Peck and Olsen 213). Other methods that do not rely on these assumptions should be used to ensure no such mistakes are committed.
Estimation Results by OLS
The tests, in this case, are conducted at a 95% level of significance. The value of the level of significance α = 0.05. The test will involve comparing the level of significance and the p-value of the specific variables. The test criterion is that if the p-value is less than the level of significance, then the variable is significant (Chen 25). According to the information above, X1 has a p-value is 0.0860 which is higher than the level of significance.
This means that the variable X1 is a significant determinant of Y. All the p-values of the independent variables are greater than the level of significance meaning that all the variables are significant determinants of the dependent variable Y. considering the real names of the independent variables, we obtain that in the model (FDI= β0 + β 1 GDP growth + β 2 export + β 3 import + β 4 Wage+ u.), Foreign Direct Investment is significantly influenced by the GDP growth, export, import, and wages.
According to the coefficients obtained, the signs show that GDP growth rate and imports increase the level of FDI. The other factors Export and Wages have negative coefficients meaning that their increase results in a decrease in the level of FDI. The level of overall significance, measured by the F-statistic and its P-value, shows that the independent variables are jointly significant. The p-value is less than the level of significance.
Another method
The other method that is considered appropriate is the 2 Stage Least Square Method because the variables in the model are related. For example, the wage is related to GDP and consequently related to DFI. The output of this model using Eviews is as stated below:
Based on the test conducted above, the method of 2SLS also shows that the independent variables are significant determinants of the dependent variable. The overall significance measured by F-statistic shows that the variables are generally insignificant. The p-value of the F-statistic is less than the level of significance meaning that the variables are jointly insignificant (Keller 15).
Works Cited
Chen, Chunlai. Foreign Direct Investment in China: Location Determinants, Investor Differences and Economic Impacts, London: Edward Elgar Publishing, 2011. Print.
Graham, Edward, and E. Wada. Foreign Direct Investment in China: Effects on Growth and Economic Performance, Oxford: Oxford University Press, 2001. Print.
Keller, Gerald. Statistics for Management and Economics, New York: Cengage Learning, 2011. Print.
Peck, Roxy, and C. Olsen. Introduction to Statistics & Data Analysis: Enhanced Edition, New York: Cengage Learning, 2008. Print.
Rubin, Allen. Statistics for Evidence-based Practice and Evaluation, London: Cengage Learning, 2010. Print.