tiểu luận kinh tế lượng the effect of variables on foreign direct investment (FDI) is based on data of over 30 countries worldwide

FOREIGN TRADE UNIVERSITY FACULTY OF INTERNATIONAL ECONOMICS =====000===== REPORT ECONOMETRICS The effect of variables on Foreign Direct Investment FDI is based on data of over 30 countri

FOREIGN TRADE UNIVERSITY FACULTY OF INTERNATIONAL ECONOMICS

=====000=====

REPORT ECONOMETRICS

The effect of variables on Foreign Direct Investment (FDI) is

based on data of over 30 countries worldwide

Class: K57 Japanese Style International Business Students: Tran Thi Van Anh – 1815520235

Kieu Thu Trang – 1815520231 Pham Thuy Trang - 1815520235 Instructor: Dr Tu Thuy Anh

Hà Nội – 10/2019

Table of Contents

1 INTRODUCTION: 2

2 LITERATURE OVERVIEW: 3

2.1 Topic introduction: 3

2.2 Literature review: 3

2.3 Procedure and program used 5

3 METHODOLOGY: 5

3.1 Specifying the object for modeling: 5

3.2 Data gatherings: 6

3.3 Data description 7

4 REGRESSION MODEL AND ESTIMATED RESULTS: 8

4.1 Regression function: 8

4.2 Analysis of correlation between variables: 8

4.3 Estimation results and the meanings: 9

5 HYPOTHESIS TESTING: 10

5.1 Testing an individual regression coefficient: 10

5.2 Testing the overall significance of the model: 12

6 SUMMARIZE THE RESULT 16

CONCLUSION 17

REFERENCES 19

1 INTRODUCTION:

In today’s world, economy is one of the most meaningful sciences that determine the social development in general and the national growth in particular What is mentioned is that econometrics is an essential subject, involved in any human resources training, facilitating the development of an economy The specificity of econometrics is the demand for quantitative analysis of the economic phenomenon, the verification of relevant model elements and reliability of the hypotheses, strategy determination and prediction All of these important features have made the econometrics more and more prosperous and closer to economics students When studying this subject, students will have a good grasp and acquire the intensiveness knowledge about the data analysis on the factors that affect the problem Therefore,

we can set right orientations, develop and find out solution to it

After a period of learning the basic knowledge of econometrics under the instruction

of lecturer Tu Thuy Anh, our group has obtained a great amount of information, which

significantly helps us to accomplish our report on the topic “The effect of variables on Foreign Direct Investment (FDI) is based on data of over 30 countries worldwide“ A foreign direct investment (FDI) is an investment made by a firm or

individual in one country into business interests located in another country Generally, FDI takes place when an investor establishes foreign business operations or acquires foreign business assets in a foreign company However, FDIs are distinguished from

companies

The goal of the investors, especially the private investors when making investment, is

to get as much profit as possible Therefore, they cannot be satisfied with domestic market but have to find a way to reach out to foreign markets In order to penetrate foreign markets, investors can use many different ways (export, conduct FDI, franchising, .) The problem for investors is to select the appropriate form of intrusion,

bring the highest efficiency and contribute to the goal of maximizing profits As a result, our team is working on this topic to identify the factors that affect the use of FDI in countries by qualifying the relationship between them and the level of FDI However, due to the lack of experience and limitation in knowledge and skills, we might have some mistakes in the report We would be very grateful to any of your comments for further improvement

Thank you!

2 LITERATURE OVERVIEW:

2.1 Topic introduction:

In this modern society, with the strong development of globalization, businesses and companies often apply FDI to expand markets and find new customers However, they can not make decisions without considering some aspects that will have an impact on FDI, such as Gross Domestic Product (GDP) and Export Therefore, we decided to

choose the topic ”The effect of variables on Foreign Direct Investment (FDI) is

based on data of over 30 countries worldwide” for our assignment, with a view to

giving a closer look to the relationship between GDP, Export and FDI and draw out some strategies in using FDI

2.2 Literature review:

There have been a lot of documents and researches about the relationship between the three following factors: Foreign Direct Investment, Gross Domestic Product and Export

Sultan (2013) said that Foreign Direct Investment (FDI) plays an important role in promoting

export and economic growth of an economy It is argued that FDI promotes exports of the host countries by increasing the productivity and productive capacity of the host country by increasing capital stock, transfer of technology, managerial skills and upgrading the skills of the local workforce through training Further, FDI also increases the opportunity for the host countries to export by facilitating access to the new and large foreign markets.

However, despite these, there has not been much study on the relationship between FDI,

export and economic growth Kishor Sharma (2000) study covers only few years of the

reform period i.e up to 1997 In order to fill this gap, the present paper tries to examine the relationship between FDI inflow and exports

It promotes exports by facilitating the host countries access to customers in global, regional and home-country markets In addition, host countries 1 Parent Institute: Assistant Professor, P.G Department of Economics, L.S College, Muzaffarpur, B.R.A.Bihar University, Muzaffarpur, Bihar, India Journal of Economics and Sustainable Development sometimes also get benefits of lobbying activities of the MNCs in their home countries for favorable treatment of exports from their affiliates abroad as happened in case of US, China etc FDI also helps in improving productivity of labour force by providing training to the local workforce and upgrading technical and managerial skills These activities benefit the country’s exports through improvement in productivity of the labor force This is especially true for export-oriented investments in advanced technological capabilities

Secondly, FDI plays an important part in affecting GDP as well Nuzhat Falki (2009)

examined the Impact of FDI on Economic Growth of Pakistan She collected the data of FDI from the Handbook of Pakistan Economy - 2005 published by the State of Pakistan and the World Bank Development indicators - 2008 from 1980 to 2006 with variables of domestic capital, foreign owned capital and labor force With the help of endogenous growth theory and applying the regression analysis she concluded that FDI has negative statically

insignificant relationship between GDP and FDI inflows in Pakistan Anokye M Adam &

George Pardeep Agarwal (2000) founded that the increase in FDI inflows in South Asia

were associated with a many-fold increase in the investment by national investors, suggesting

that there exist linkage effects between FDI and GDP the impact of FDI on GDO growth is found to be negative prior to 1980, mildly positive for early eighties and strongly positive over the late eighties and nineties

However, there were no studies about how Gross Domestic Product and Export affect

variables on Foreign Direct Investment (FDI) is based on data of over 30 countries worldwide” with a view to bring about a new perspective on how these factors affect on

each other the way around After that, we will draw out some recommendations for the economists in particular and the whole economy in general We hope that the readers can make some comments on our project and continue to develop it in the future

2.3 Procedure and program used

Procedure:

Step 1: Topic Introduction

Step 2: Economic model

Step 3: Econometric model

Step 4: Data collection

Step 5: Estimation of econometric model

Step 6: Check multicollinearity and heteroscedasticity

Step 7: Hypothesis postulated

Step 8: Result analysis & Policy implication

Gretl program is primarily used to analyze the data and run the regression

3 METHODOLOGY:

As data are provided up front, the economic model used in this report is an empirical one Note that the fundamental model is mathematical; with an empirical model, however, data is gathered for the variables and using accepted statistical techniques, the data are used to provide estimates of the model's values Empirical model discovery and theory evaluation are suggested to involve five key steps, but for the limitation of purpose and resources, this part of the report only follows three of them: (1) specifying the object for modeling, (2) defining the target for modeling, (3) embedding that target in a general unrestricted model

3.1 Specifying the object for modeling:

= ( )

(1)

As such, this report finds the relationship between Foreign Direct Investment, which is the object for modeling, and each of relating factors including Gross Domestic Product and Export

3.2 Data gatherings:

We use data.worldbank.org, which have been verified to be highly accurate to gather

Data about Foreign Direct Investment, Gross Domestic Product and Export in over 30 countries The Link will be in the References part Our data is shown in the following exhibit:

Exhibit 2: Figure of GDP, FDI and Export in 34 countries (unit: million USD)

3.3 Data description

After some discussions as well as taking the meaning of each variable into consideration, we decided to choose the variables for our regression model as follows: The dependent variable chosen is the level of FDI in over 30 countries, denoted as FDI The independent variables include two factors: the total amount of Gross Domestic Product (GDP) of each country, denoted as GDP; the total amount of money gained through Exporting, denoted as Export

- Dependent variable: FDI

- Independent variables (including 2 variables) :

+ X1 : GDP (million USD) + X2 : Export (million USD)

A brief description of each variable is given in Exhibit 1:

Exhibit 2: Description of Variables

4 REGRESSION MODEL AND ESTIMATED RESULTS:

4.1 Regression function:

We have one dependent variable, denoted as FDI (Foreign Direct Investment) and two independent variables, denoted respectively as GDP (Gross Domestic Product), Export Thus, we can construct the regression function to demonstrate the relationship between Y and X as follows:

Where:

- 0 : intercept of regression model

- ̂ : estimator of

0 0

,

4.2 Analysis of correlation between variables:

We use command “correlation matrix” from Gretl to get the table of correlation

between variables as follows:

8

As can be seen from the table:

- Correlation coefficient between GDP and FDI is -0.4038

- Correlation coefficient between GDP and Export is 0.9055 > 0.8

- Correlation coefficient between FDI and Export is -0.1685

 Therefore, multicollinearity happens in this model.

4.3 Estimation results and the meanings:

With the data collected, we run the regression model and have the table as follows:

Based on the data collected from the table, we establish the sample regression function:

 Meanings of the regression coefficients: ̂ = -7110.31: the intercept of sample regression equals to -7110.31, which

means that when all the independent variables are zero, the expected value of FDI is -7110.31

 ̂ = –0.0223044: the estimator of slope coefficient of variable GDP equals

to –0.0223044 This figure indicates that when GDP rises by 1 unit, the

9

expected value of their FDI decreases by 0.0223044, in the condition that other things are held constant

 ̂

= 0.0778029: the estimator of slope coefficient of variable Export equals to 0.0778029 This figure points

out that when Export of goods and services increases by 1 unit, the expected value of FDI increases by 0.0778029, in the condition that other things are held constant.

The coefficient of determination= 0.378838 indicates that all the independent

variables (GDP, Export) jointly can explains 37.8838% of the variation of the

dependent variable (FDI)

The other factors (except for GDP and Export) can explain 62.1162% of

the variation of the dependent variable (FDI)

 Other results

 S.D dependent var = 38037.11

 S.E of Regression = 30930.43

5 HYPOTHESIS TESTING:

In order to find out whether given observations are compatible with

stated hypothesis or not, we do the hypothesis testing as follows:

5.1 Testing an individual regression coefficient:

5.1.1 The T-test:

10

The purpose of this is to test the influence of independent variable, which includes GDP on the expected value of dependent variable, which is myopia In this section, we use two-sided testing with the pair of hypothesis: { 0: = 0

Based on the data collected from Gretl table below, we have:

 Testing the coefficient of time:Firstly, we establish a pair of hypotheses: { 0: = 0

0.025

Since | |> 032.025 , we reject H 0 , accept H 1. In other words, the slope coefficient of variable GDP is different from zero.

11

Conclusion: At the level of significance 5% , the slope coefficient of variable GDP is

statistically significant

5.1.2 The P-value method

We can also use P-value method to test the coefficient of variables

Firstly, we have a pair of hypotheses: { 0: = 0

Based on the data from Gretl, it can be clearly seen that:

 It is smaller than the level of significance ( = 0.05), then we reject H 0 and accept H 1 Therefore, all the regression coefficients are statistically significant.

The results we have from P-value are matched with the outcomes from T-test above

5.2 Testing the overall significance of the model:

This F-test evaluates the null hypothesis that all the coefficients of independent variables are equal to zero versus the alternative that at least one does not

/We establish a pair of hypothesis as follows:

12

0 : b = 0 2 = 0

{

GDP

0: R

Then, we compute the test statistic:

2 (−)

= (1 − 2 )( − 1) = 6.236

F 0.05 (1,32) = 4.15

We have F > F 0.05 (3,66); therefore, we reject H 0 and accept H 1

5.2.1 Heteroscedasticity testing:

We establish a pair of hypotheses as follows:

{

1: The residuals are heteroscedastic

Then, we use the command “ Breusch-Pagan test for heteroskedasticity ” in Gretl

and have this following result:

13

As can be clearly seen from the table, the P-value associated to the heteroscedasticity test is greater than threshold (P-value = 0.543 >0.05) Thus, we cannot reject the null hypothesis that the residuals are homoscedastic

→ We accept H 0 and reject H 1

We also use command gretl and have this graph:

We can observe that while the average of the residual is always zero, its spread

around its mean does seem to depend on the area This is an indication of

heteroscedasticity A more formal test is a regression of the square of the residuals on the explanatory variable(s)