(Tiểu luận) the relationship between electrical machinery equipment exports (hs code 85) and economic growth in vietnam from 2001 to 2020

Trang 1 FOREIGN TRADE UNIVERSITY HO CHI MINH CAMPUS MIDTERM PROJECTECONOMETRICS THE RELATIONSHIP BETWEEN ELECTRICAL MACHINERY & EQUIPMENT EXPORTS HS CODE 85 AND ECONOMIC GROWTH IN VIETN

FOREIGN TRADE UNIVERSITY

HO CHI MINH CAMPUS

Team 5 Class: K59CLC6 Class ID: 73 Supervisors: Mrs Le Hang My Hanh

Ho Chi Minh City, April 2022

GROUP OF AUTHORS

TABLE OF CONTENT TABLE OF CONTENT I

TABLE OF TABLE III

CHAPTER 1: INTRODUCTION 1

1.1 RATIONALE OF THE RESEARCH

1.2 AIMS AND OBJECTIVES

1.3 SCOPE OF THE RESEARCH

1.4 RESEARCH QUESTIONS

1.5 RESEARCH METHODS

1.6 METHOD OF DATA ANALYSIS

CHAPTER 2: LITERATURE REVIEW 4

2.1 THEORATICAL BASIS

2.2 PREVIOUS RESEARCH MODELS

2.2.1 Domestic research

2.2.2 Foreign research

2.2.3 Research capacity

CHAPTER 3: RESEARCH METHOD AND DATA 8

3.1 RESEARCH METHOD

3.1.1 Variable descriptions: 8

3.1.2 Brief justification of explanatory variables 10

3.1.2.1 Government spending (gov ) of vietnam t 10

3.1.2.2 Investment (FDI t): 11

3.1.2.3 Labor (LAB t): 12

3.1.2.4 Export (EX t): 14

3.1.2.5 Setting up a research model 15

3.2 DATA COLLECTION AND PROCESSING

3.2.1 Data collection methods 16

3.2.2 Data processing method 17

3.2.2.1 Data processing software STATA – 17

3.2.2.2 Data processing methods 17

3.2.3 Data

CHAPTER 4: RUN STATA 19

4.1 MULTIPLE REGRESSION MODEL

4.1.1 Multiple regression model 19

4.1.2 Meaning of regression coefficients 19

4.1.3 Hypothesis testing of regression coefficients 20

4.1.3.1 Test β1 20

4.1.3.2 Test β2 20

4.1.3.3 Test β3 20

4.1.3.4 Test β4 21

4.1.4 Test of the overall significance of the regression 21

4.1.5 Measure of goodness of fit of the estimated regression 22

4.2 CHECK THE MODEL'S DEFECT

4.2.1 Multicollinearity 2

4.2.1.1 The detection of Multicollinearity 22

4.2.1.2 Remedies for Multicollinearity 25

b Drop LFDI (2) 27

c Drop LEX (3) 28

d Drop LGOV (4) 29

e Drop LLAB, LGOV (5) 30

4.2.1.3 Building and testing new model 31

4.2.2 Detecting heteroscedasticity 33

4.2.2.1 Park Test 33

4.2.2.2 Breusch-Pagan-Godfrey Test 34

4.2.2.3 White’s General Heteroscedasticity Test 34

4.2.3 General analysis 3

CHAPTER 5: CONCLUSION, LIMITATIONS AND POLICY PROPOSED 37

5.1 CONCLUSION

5.2 LIMITATIONS:

5.3 PROPOSING SOME SOLUTIONS TO INCREASE VIETNAM’S GDP 39

5.3.1 Export

5.3.2 FDI

REFERENCES III

APPENDIX VI

TABLE OF TABLE

Table 1: Variables’s description 10 Table 2: Auxiliary regression for each explanatory variable 24

CHAPTER 1: INTRODUCTION

In the context of international economic integration, the relationship between exports and economic growth is a frequently discussed topic According to figures and events reviewed by GSO, economic growth is the increase in the amount of production

an economy produces over time On that basis, researchers can provide orientations and policies for development in the next period Specifically, GDP is an aggregate economic indicator, used as an indicator of economic development That is why GDP is used by most countries in the world to evaluate economic growth

In macroeconomics, export is an element in GDP, so the development of exports can play an important role in the economic growth of a country This has been proven

by many ancient economists such as Adam Smith và David Ricardo Based on these theoretical works, a series of empirical studies have been conducted, using national, regional, and international data samples to elucidate the relationship between exports and economic growth Nevertheless, there are still few research papers that study the relationship of a specific export commodity to the economy

Specifically, the electronics industry is a manufacturing industry with an important strategic position in the economy and has a strong impact on other industries Especially, the export of electrical machinery and equipment (HS code 85) accounts for nearly 40%

of the total export turnover According to the report of the Ministry of Industry and Trade, Vietnam has risen to the group of key exporters of electronic goods, from 47th place in 2001 to 11th place in 2020 According to Vietnam's electronic industry master plan in the 2016 - 2020 period, the growth of the electronics industry in the 2016 - 2020 period will reach 23.8%/year; the vision by 2030 to reach 19-21%/year

With that strong development, the government wishes to set the goal of building the electronics industry to become a key industry and create a support base for other

lượng 100% (8)

17

ĐỀ Kinh Te Luong TEST1

kinh tế

lượng 100% (6)

9

Ý NGHĨA BẢNG HỒI QUY MÔ HÌNH BẰN…kinh tế

lượng 100% (5)

18

Tiểu luận Kinh tế lượng - nhóm 11-đã…kinh tế

lượng 100% (5)

30

Tiểu-luận đức-kinh-doanh-…

-Đạo-25

2industries to develop This also helps contribute to Vietnam's economic growth in the future

Because of this reason, we conduct this research with a desire to test the relationship between Electrical machinery and equipment exportation and economic growth in Vietnam from 2001 to 2020 to clarify whether this commodity really has a

large impact on the economic growth of Vietnam or not

The research is conducted with an aim to clarify the importance of a highly exported commodity on the economic development of Vietnam The result can help Vietnam’s government pay more attention to developing strong industries, from that can have more basis for issuing policies and strategies for economic development as a whole,

as well as opening up further research directions for following research papers

This research used time-series data for a period of 20 years from 2001 to 2020 in Vietnam Independent variables that are put in the model have contributions to the GDP

of the country and relate to the problem that this report is focused on analyzing, including foreign direct investment (FDI), government spending (GOV), labor (LAB), and Electrical machinery and equipment export (hs code 85) With the scope is that: FDI is invested into Vietnam; total government spending by the Vietnamese government; labor working within Vietnam; and the commodity exports from Vietnam to the world

What is the relationship between the exportation of Electrical machinery and equipment export (hs code 85) and economic growth?

How is the development of electrical machinery and equipment export (hs code 85)

in Viet Nam over the past twenty years?

lượng 100% (4)

ĐỀ ÔN THI KINH TẾ LƯỢNG CUỐI KÌkinh tế

lượng 100% (4)

42

Besides exportation, how have other factors affected economic growth in Vietnam

in the past 20 years?

What policies can the government introduce to increase the export of Electrical machinery and equipment export (hs code 85) to promote economic growth?

The figures in this study are quantitative data, all data analyzed are quantitative figures The data source used for the study is the secondary data source, which has been compiled in advance and collected for processing These numbers are taken from Trademap, General Statistics Office and other official statistics channels of Vietnam and the world

The method that we use to analyse the data in this study is the quantitative analysis method Data will be synthesized and analyzed through the variable description and regression model building The variables will be observed through a multiple regression model expressed in natural logarithms

Multiple regression model:

LGDPt= β0+ β1LLABt+ β2LGOVt+ β3LFDIt + β4LEXt + e i

where LGDP is a dependent variable and LFDI, LLAB, LGOV, LEX are independent variables.F

CHAPTER 2: LITERATURE REVIEW

The relationship between exports and economic growth has been analyzed in many recent empirical studies However, the evidence for this relationship is quite varied While some studies show the existence of a causal relationship between exports and economic growth, others suggest that there is no positive relationship between these two factors

There are two views on the issue of export-led economic growth Some dissenters argue that boosting export growth will not lead to a higher GDP growth rate, if other conditions remain unchanged, and/or some other preconditions do not is satisfied There have been many studies showing a lackluster role of exports in GDP growth in a number

of countries and groups of countries

Others are in favor of export-led economic growth, and they argue that there is a vast body of scholarly research on the role of (exports) trade in economic growth, at least starting with It begins with the arguments of hundreds of years ago by economists such

as Adam Smith and David Ricardo, and is most recently followed by a series of theoretical works by other prominent economists such as Romer, Grossman, Helpman, Baldwin, Feder and Forslid, etc - theoretical works that paved the way for the systematic and scientifically sound understanding and analysis of the relationship between exports and growth Based on these theoretical works, a series of empirical studies have been conducted, using national, regional and international data samples to elucidate this relationship These empirical studies tend to confirm that exports are positively associated with economic growth The successful outward development model of East Asian countries over the past decades is a strong testament to the role of exports as an engine of economic growth in this region

However, it can be asserted that most researchers agree that export growth is one

of the main factors leading to economic growth (ie, assuming export-led growth) This

theory is based on the premise that increased exports can affect economic growth through

a number of channels First, export industries can influence non-export industries through positive externalities Furthermore, export expansion will increase the efficiency

of economies of scale In addition, exports can reduce foreign currency difficulties and thus can help countries access global markets more easily

2.2.1 Domestic research

There had been many domestic research papers that have researched and tested the relationship between exports and economic growth in Vietnam Each study uses different and very diverse models, such as an extended Cobb-Duglas model of accounting for economic growth resources, a vector autoregression model (VAR), Multivariate regression function (MRF), Feder Model (1982), Balassa Model (1978), Granger Model (1969) Each research paper also has different methods of sampling and taking variables:

as in her master's thesis defense thesis, Ms N.T.M.Linh (UFM) used time-series data collected on a quarterly basis of Vietnam's economic growth and export value in the period from the first quarter of 2002 to the first quarter of 2018 Mr N.M.Hai's research paper (BUH) takes data on GDP, capital (K), labor (L) collected from the General Statistics Office of Vietnam (GSO) on a quarterly basis, from the first quarter of 2000 to the fourth quarter of 2017, a total of 72 observations; and a research paper by master P.T.Cong published in Science journal, Vietnam National University (VNU) used data for regression analysis including data on exports, domestic and foreign investment, GDP growth rate, and employment of 55 people provinces and cities throughout the country

in the period 1996-2004

The research results show that the relationship between exports and economic growth in Vietnam is a two-way relationship On the first hand is that exports help increase capital, create more jobs and promote technological progress, thereby promoting economic growth On the other hand, rapid economic growth increases Vietnam's competitive advantage in the international market, thereby boosting exports

Not only that, but research results also show that exports play an important role not only

in accelerating the country's economic growth but also in positively contributing to the development of non-export factors such as infrastructure, electricity, water, processed food, etc.) in the country

2.2.2 Foreign research

The study, conducted by two authors, Mohsen Bahmani-Oskooee and Maharouf Oyolola, applies this new approach to export and output data from 44 developing countries and provides support for the growth hypothesis export-led in 60% of countries The short- and long-run relationship between export growth and economic growth has received a lot of attention in the literature Cointegration techniques have been used by previous researchers that require the variables to be non-stationary, but that their linear association must be stationary When the variables are not integrated in the same order, they are excluded from the analysis This need not happen with the advent of the limited testing method Indeed, this method does not require root unit testing This paper applies this novel approach to exporting and exporting data from 44 developing countries and provides support for the export-led growth hypothesis in 60% of the countries As a result, in the short run, export growth has a short-run effect on output growth The general conclusion of the study is that export growth has both short- and long-term effects on output growth in most developing countries

According to the study EXPORTS AND ECONOMIC GROWTH: Further evidence was studied by Bela BALASSA He studied the relationship between exports and economic growth in a group of eleven developing countries that formed an industrial base In this study, the author used qualitative methods to research and make assessments

on the relationship between exports and economic growth The results from Balassa's study indicate that trade orientation is an important factor contributing to cross-country differences in income growth This analysis was based on previous studies and evaluation analysis, however, this analysis did not show the model and the collected and processed data to test the hypothesis

In general, from the research papers on the foreign convention, both qualitative and quantitative studies show a positive relationship between exports and economic growth 2.2.3 Research capacity

Through the previous research topics, we can see that the main research topics are about the relationship between macro factors affecting economic growth such as import and export, labor resources, investment, Their research model uses variables that represent the factors and indexes of an entire country Accordingly, we can see that the impact of those factors will theoretically have a negative or positive effect on GDP However, there have been many studies and proved that the factor of total export turnover of a country has a positive effect on GDP But there are very few topics that deal with what a country's largest export industry means and what impact it has on economic growth Or there is also a research topic but mainly based on qualitative research methods, the model has not been shown

Therefore, this research topic has brought a new perspective to the study of Electrical machinery and equipment and their parts; sound recorders and reproducers, television on economic growth in Vietnam

CHAPTER 3: RESEARCH METHOD AND DATA

at time t

The increase in disbursed FDI will expand the production scale

of economic sectors, thereby creating conditions to promote economic growth

of people in working age

in Vietnam at time t

population of working age increases, the larger the gross domestic product, which promotes faster economic growth

a stable and favorable socio-economic environment favorable conditions for economic growth

electrical machines and equipment by

time t

billion USD (+)

Exports have positive effects

on the trade balance, the higher the export,

the more the trade balance tends to increase, which has a positive impact on GDP

Table 1: Variables’s description

3.1.2 Brief justification of explanatory variables

Based on previous research on Vietnam's economy in terms of macroeconomics and some Southeast Asia countries whose economies have some of the same basic features as Vietnam's also areas in the world, our study decided to include the following components in the model and analyze the impact they have on Vietnam's net export, and lead impacts on Vietnam's economic growth

3.1.2.1 Government spending (gov ) of vietnam t

In paper “The Effects of Public Spending Shocks on Trade Balances in the European Union” by Roel Beetsma (2007), they have explored the effects of government spending on trade balances and budget deficits in the European Union To this end, they employed an annual panel VAR with exports and imports as separate variables and constructed the responses of trade balances and budget balances from their composing variables Their baseline estimates suggest the presence of a Keynesian multiplier of government spending A one-percent of GDP increase in government spending produces

a 1.2% impact increase in GDP and a 1.6% peak increase The trade balance deteriorates because imports rise and exports fall Their estimates suggest an impactful fall of the trade balance by 0.5% of GDP and a peak fall by 0.8% of GDP Moreover, the government spending increase produces a 0.7% of GDP impact (and peak) budget deficit, thereby pointing to the potential relevance of the twin deficits hypothesis Besides, several researchers use the Granger causality test to determine whether government expenditures cause economic growth or economic growth causes government expenditures Based on the results from Jiranyakul et al (2017) with the

topic "The Relationship between Government Expenditures and Economic Growth in Thailand" show that aggregate government expenditures cause economic growth, but economic growth does not cause government expenditures to expand In other words, there is a unidirectional causality between government expenditures and economic growth Further investigation using the ordinary least square method shows that government spending and its one-period lag variable impose a highly significant impact

on economic growth, which confirms the results of the causality test The findings here support the Keynesian approach which stipulates that causality runs from government spending to economic growth

Based on the above results, it can be confirmed that Government spending has a close relationship with exports and GDP

H1: Government spending (GOV ) of Vietnam is positively related to Gross t

domestic product (GDP) of Vietnam (β1 > 0)

3.1.2.2 Investment (FDI t):

According to the study of Agiomirgianakis, Asteriou, and Papathoma (2003) on the impact of GDP growth on countries of the Organization for Economic Cooperation and Development, it shows a positive relationship between GDP and FDI in developing countries Hansen (2006) analysis of causality Granger, Srinivasan, (2010) investigated the economy of the Association of Southeast Asian Nations (ASEAN), Hsiao (2006) estimated the VAR of three variables to find out Granger causality is different for each

of the eight economies and Liu (2002) gives similar results Not only that, in a recent study by Riedl (2010) to answer the question "Does GDP affect FDI?", through 140 tests,

it was concluded that there is an intimate relationship between GDP AND FDI Chowdhury's study using the bootstrap test demonstrates strong evidence for a bidirectional causal relationship between the two variables In addition, Tang, (2008), Basu, (2003), Hsiao (2006) show a one-way causal relationship from FDI to domestic investment and economic growth Instead of crowding out domestic investment, FDI is seen as complementary to domestic investment

The causality results of panel data Hsiao (2006) show that FDI has a one-way effect

on GDP directly and indirectly through exports, and also exists a two-way causal relationship between exports and GDP According to Mohsen Mehrara (2011) and Javed and Farooq (2009) in Pakistan, the relationship between exports and economic growth was of interest to researchers and policymakers in the early 1960s Research by Ullah et al., (2009), Jung and Marshall (1985), Chow (1987), Kugler (1991) and Islam (1998) shows that increased exports will lead to growth, through supportive policies Export subsidies or exchange rate changes will increase GDP Henriques and Sadorsky (1996), Sharma and Panagiotidis (2005) suggest that there is an opposite effect compared to the above conclusion Besides, there are also studies that show that exports and economic growth have an interaction, some studies have proved this relationship Dutt and Ghosh (1994), Thornton (1997), Khalafalla and Webb (2001)

FDI is a component of the economy, contributing to the overall growth of the whole economy Foreign investment contributes to promoting economic growth, improving the efficiency of using domestic investment resources FDI contributes to changing the structure of export products in the direction of reducing the proportion of mining products and primary products, and gradually increasing the proportion of manufactured goods FDI positively affects the expansion of export markets FDI also contributes to stabilizing the domestic market, limiting the trade deficit by providing the domestic market with high-quality products manufactured by domestic enterprises instead of having to import as before Because of the advantages that FDI brings, it has contributed

to export (EX) and the growth of gross domestic product (GDP)

H2: Investment (FDI ) of Vietnam is positively related to Gross domestic product t

(GDP) of Vietnam (β2 > 0)

3.1.2.3 Labor (LAB t):

According to the research paper: The Labor Impact of Lao Export Growth in February 2016 from World bank Group The authors test empirically for a correlation between exporting and labor outcomes, and whether there is evidence of causality They

use firm- vel data to estimate the quasi-elasticity of employment and wages with respect le

to the share of exports in total sales for Lao PDR, as well as a global sample of countries The regression analysis finds insignificant effects for the Lao PDR sample (likely due to its small size), and statistically significant but small positive correlations between export share and employment (for total, skilled and unskilled) for the global sample of firms Many researchers have proposed economic models to determine the relationship between economic growth and employment Kapsos (2005) and Dopke (2001) show that there is a positive relationship between economic growth and employment Schmid (2008) argues that economic growth (width or depth) is an important determinant of job creation Thus, economic growth is the response to the growth of aggregate demand, which can be achieved in different states, either an increase in the number of inputs (labor force, capital, etc.) or the productivity of other factors production (growth in depth), or

a combination of both

In the research paper "The relationship between economic growth and employment

in Vietnam" (2015) by Pham Hong Manh The results of regression model analysis show that the statistics F and t both indicate a relatively good presence of the input data For the economy as a whole: α - the elasticity of output value to capital, equal to 0.22, meaning that increasing investment capital by 1% of GDP will increase by 0.22%; β - the elasticity of output value to labor, equal to 1.71, meaning that increasing the number

of workers by 1% GDP will increase by 1.71%; (α + β) > 1 means that the production function has increasing returns to scale The GDP of the economy increases at a higher rate than the growth of labor and investment capital of the whole society

Besides, Vietnam is one of the economies with the largest trade scale in the world, according to data from Trademap in 2020 Vietnam's export value reached more than 280 billion USD Exports that account for a high proportion are mainly industrial and garment products, which are labor-intensive goods Therefore, the authors decided to include the Labor factor (LABt) in the model to evaluate in the short and long term the correlation between Labor and Export and GDP

H3: Labor of Vietnam is positively related to Gross domestic product (GDP) of Vietnam (β3 > 0)

3.1.2.4 Export (EX t):

The causality results of panel data Hsiao (2006) show that beside FDI has a way effect on GDP directly and indirectly through exports, there exists a two-way causal relationship between exports and GDP According to Mohsen Mehrara (2011) and Javed and Farooq (2009) in Pakistan, the relationship between exports and economic growth was of interest to researchers and policymakers in the early 1960s Research by Ullah et

one-al (2009), Jung and Marshall (1985), Chow (1987), Kugler (1991) and Islam (1998) shows that increased exports will lead to growth, through supportive policies Export subsidies or exchange rate changes will increase GDP Henriques and Sadorsky (1996), Sharma and Panagiotidis (2005) suggest that there is an opposite effect compared to the above conclusion Besides, there are also studies that show that exports and economic growth have an interaction, some studies have proved this relationship Dutt and Ghosh (1994), Thornton (1997), Khalafalla and Webb (2001)

In Vietnam, Mr Phan The Cong analyzed the relationship between exports and GDP in the scientific journal Hanoi National University published in 2011 By using the Feder model (1982) , Balassa (1978), Granger (1969) and modified and supplemented models for the period 1996-2006, the article examined the impact of 8 exports on economic growth according to provincial data in Vietnam The analysis provided an empirical evidence for the export-based economic growth theory; It also shows that exports play an important role in accelerating the country's economic growth and actively contribute to the development of non-export factors (such as electricity, water, infrastructure, etc.) floors, processed foods ) in the country

With the above results, it can be confirmed that exports have a close relationship with GDP

H4: Export of Vietnam is positively related to Gross domestic product (GDP) of Vietnam (β4 > 0)

3.1.2.5 Setting up a research model

According to preliminary researches of Vietnam and foreign countries, the selected model to analyze the factors affecting on economic growth is multyiple regression

Based on the economical effect on dependent variable, which is GDP, the model describing the relationship of socio-economic factors with Vietnam economic growth

is set:

GDP = f(FDI, LAB, GOV, EX)

Where:

and equipment and parts thereof; sound recorders and reproducers, television image and sound recorders and reproducers, and parts and accessories of such articles) to the world

As similar to previous studies, all variables are expressed in natural logarithms:

LGDPt= β0+ β1LLABt + β2LGOVt+ β3LFDIt + β4LEXt + ei

Where:

β0: constant

β β1, 2, β , β3 4 : regression coefficients

ei: error term

LGDP is a dependent variable and LFDI, LLAB, LGOV, LEX are independent variables

3.2.1 Data collection methods

The data used in the study is the annual data of Vietnam for the period from 2001

to 2020, collected from the following sources:

a Dependent variable (GDP)

The dependent variable selected in the study is Vietnam's gross domestic product

in the period 2001-2020 The data is taken from the website of the World Bank (https://www.worldbank.org/en/home)

b Independent variables

The number of people in working age in Vietnam (LAB): The data in Vietnam for the period 2001-2020 are taken from the website of the General Statistics Office of Vietnam

Total export of electrical machines and equipment by Vietnam (EX): Export data of electrical machinery & equipment industry products of Vietnam used for research in the period 2001-2020 are collected at Trade Map

https://www.trademap.org/Index.aspx

3.2.2 Data processing method

3.2.2.1 Data processing software – STATA

Currently, STATA is one of the most used data processing software besides EVIEW, SPSS, R STATA was developed in 1985 by StataCorp, whose name originates from the combination of "Statistics" and "Data" This is software that is trusted

by users working in the research field, especially in economics, political science and sociology

In terms of strengths, STATA is loved by many new users because of its ease of use and data visualization Powerful as well as simple data management capabilities, allowing to perform many complex commands with data easily And especially the biggest strength of STATA is the regressions, thanks to the ease of use of the regression prediction tools However, STATA also has many weaknesses in analysis of variance and multi-dimensional analysis of communication (multi-dimensional analysis of variance, group analysis) Recognizing the special requirements of the thesis topic, the group decided to use STATA for the purpose of data processing of the topic

3.2.2.2 Data processing methods

The regression method used to estimate the model's parameters is the ordinary least squares (OLS) method The OLS used to select the final regression model is the general

to specific modeling technique In OLS, the p value (p_value) is defined as the lowest level of significance at which the hypothesis H0 (the assumption that the independent variable under consideration has no significance for the dependent variable) can be rejected, whereby the test p-value is considered as a way to test the statistical significance

of the independent variable When the confidence interval is 95% (significance level is 5%), an independent variable is statistically significant when its p-value is less than 0.05

So the smaller the p_value, the more statistically significant the model is By applying the method from general to specific to choose the final regression model, the initial research model is quantified to get the initial regression function The independent variable with the largest p value and greater than the significance level of 0.05 will be excluded from the model Then the new models will be tested so that the final result is a model with all the explanatory variables satisfying p_value < 0.05 Then all independent variables in the model are statistically significant (with significance level of 5%) In addition, there are two assumptions of the OLS method that need to be taken into account: (1) the random errors Ui are not correlated with each other and (2) the errors Ui are random quantities with zero variance change Therefore, when the model has ensured that the independent variables are all statistically significant, the team will conduct tests to detect defects related to Multicollinearity and Variance From there, propose and implement appropriate remedial methods

3.2.3 Data

Table of variables for Vietnam for the period 2001-2020

CHAPTER 4: RUN STATA

Before running regression, we set up data in STATA to define the type of data, which is time-series data in this paper

4.1.1 Multiple regression model

4.1.2 Meaning of regression coefficients

β0 = 3.915: When there are no influencing factors and Vietnam does not participate

in the export of goods, the GDP is 3.915%/year

β1 = - 0.1843: With ceteris paribus, LAB increases by 1%, the GDP of Vietnam decreases by an average of 0.1843%

β2 = 0.8207: All other things being equal, an increase in GOV of 1% will increase Vietnam's GDP by an average of 0.8207%

β3 = 0.1386: All other things being equal, if FDI increases by 1%, Vietnam's GDP will increase by an average of 0.1386%

β4 = - 0.0572: Other things being equal, the EX of HS 85 products increased by 1%, the GDP of Vietnam decreased by 0.0572% on average

4.1.3 Hypothesis testing of regression coefficients

=> The number of people in working age in Vietnam has no effect on Vietnam's

gross domestic product with the significance level of 5%

=> Total foreign direct investment into Vietnam has effect on Vietnam's gross

domestic product with the significance level of 5%

4.1.3.3 Test β3

H0: β3 = 0 with the significance level of 5%

H1: β3 ≠ 0

Ta có: p_value β3=0.025 < α=0.05

=> Reject H0

=> Total amount of government spending has effect on Vietnam's gross domestic

product with the significance level of 5%

=> Total export of electrical machines and equipment by Vietnam has no effect on

Vietnam's gross domestic product with the significance level of 5%

4.1.4 Test of the overall significance of the regression

If we want to test the hypothesis that all the slope coefficients in the GDP regression are simultaneously equal to zero (β1 = β = β = β2 3 4 = 0) (suggesting that we can strongly reject the hypothesis that collectively all the explanatory variables have no impact on the GDP variable), we use the Ftest This null hypothesis can be rejected if the p value of the estimated Fvalue is very low

(Obtained from STATA)

As the table shows, the probability of obtaining such an F or greater is practically zero, suggesting that the null hypothesis can be rejected There is at least one regressor that is significantly different from zero

4.1.5 Measure of goodness of fit of the estimated regression

The coefficient of determination, denoted by R2, is an overall measure of goodness

of fit of the estimated regression line (or plane, if more than one regressor is involved), that is, it gives the proportion or percentage of the total variation in the dependent variable Y(TSS) that is explained by all the regressors

H0: R2= 0 with the significance level of 5%

H1: R2≠ 0

p_value F=0.0000< 0.05

=> Reject H0

=> The regression model economically fits wuth the significance lecel at 5%

4.2.1 Multicollinearity

4.2.1.1 The detection of Multicollinearity

Way 1: High R with low t-Statistic Values 2

Possible for individual regression coefficients to be insignificant but for the overall fit of the equation to be high but it seems to be less efficient

Way 2: High pairwise correlations among explanatory variables or regressors

It is believed that high pairwise correlations between regressors (>0.8) are a sign

of collinearity Therefore one should drop highly correlated regressors But it is not a good practice to rely on simple or bivariate correlation coefficients, because they do not hold the other variables in the model constant while computing the pairwise correlations

As figure … above,all variable pairs have high correlations (>0,8) are: LAB and FDI; LAB and LGOV; LLAB and LEX; LFDI and LGOV; LFDI and LEX; LGOV và LEX

=> Multicollinearity

Way 3: Auxiliary regressions

To find out which of the regressors are highly collinear with the other regressors included in the model, we can regress each regressor on the remaining regressors and obtain the auxiliary regressions mentioned earlier

We can test the overall significance of each regression by the F test discussed in Chapter 2 The null hypothesis here is that all the regressor coefficients in the auxiliary regression are zero If we reject this hypothesis for one or more of the auxiliary regressions, we can conclude that the auxiliary regressions with significant F values are collinear with the other variables in the model