It is thought to be a crucial issue, nevertheless, thatcould reduce the economy''''s official growth rate.The Consumer Price Index, Internet users, Population Growth Rate, TaxRevenue, Index
ABSTRACT
The shadow economy, also called the underground, informal, or parallel economy, includes illegal activities and unreported income from producing legal goods and services, either from monetary or barter transactions Therefore, any economic operations that are generally taxable and reported to the tax authorities are included in the shadow economy The relationship between the rise of the informal sector or the shadow economy and economic growth has not been clearly demonstrated by theoretical or empirical research It is thought to be a crucial issue, nevertheless, that could reduce the economy's official growth rate.
The Consumer Price Index, Internet users, Population Growth Rate, Tax Revenue, Index of Economic Freedom, Unemployment Rate, and GDP Growth are the seven variables that this study will examine in order to determine how the growth of the underground economy is influenced by each To examine the correlation between the aforementioned characteristics, we used OLS on panel data gathered from 27 European Union nations between 2008 and 2021.
Based on the regression results, we do the analysis and provide an explanation of the influence of the components, the unaffected factors, and the factors removed from the model Furthermore, we would like to offer some perspectives and recommendations on the future policy-making of corporations (or the government).
Keywords: shadow economy, European Union
3.3 Expected signs of variables and definitions: 14
5 Estimation results and diagnostic tests: 21
5.1 Analysis of estimated regression results: 21
5.2 Testing for violations of classical linear regression model assumptions 24
5.3 Remedies for violations of classical linear regression model assumptions 26
IV CONCLUSION AND POLICY IMPLICATIONS: 31
Table 3 Summary statistics of the regression model’s variables 18
Table 4 Correlation coefficients among variables using command [corr] 20
Table 6 Results for detection of multicollinearity using command [VIF] 24
Table 7 Estimated regression results after using first-difference transformation 27
Table 8 Estimated regression results after including the first-lagged dependent variable 28
Table 9 Estimated regression results after the model transformation 29
INTRODUCTION
As long as human civilization exists, the mainstream economy has been side by side and along with it, the underground economy follows Though not mainstream, the underground is still one of the crucially important aspects of a country’s general economy.
The underground economy goes by many names: shadow, informal, unobserved, unrecorded or unofficial economy Unlike its mainstream counterpart, the underground economy includes not only illegal activities but also unreported income from the production of legal goods and services, either from monetary or barter transactions
It is challenging to determine the size of underground economies because, by their very nature, they are not subject to governmental control; as a result, the economic activity neither generates tax returns nor appears in official statistical reports However, even though the transactions are hidden, keeping track of outgoing expenses can provide a sense of statistics In other words, spending that is not reflected in documented transactions presumably reflects the scope of black market activities.
It is important to look at this issue in detail, identify the root causes that determine its size and growth, and devise policies that target those causes in order to bring the majority of the underground businesses into the formal sector and enable the government and policy framework The problems of the underground economy are too numerous and damaging to ignore, and the prolonged existence of the shadow economy would ultimately reduce the overall tax revenue and damage the macroeconomic policy framework.
For this reason, we decided to conduct a research on factors affecting the economies of 27 countries within the span of 13 years This report will help dig further into those key factors as in the role they play in the countries’ economies as well as their relevance to the operation of the underground economy In this report, the content is organized as follows: The first part will be the state of knowledge in this field, the second part will present the methodological coordinates and data analysis and
H ướ ng d ẫ n t ự h ọ c môn Kinh t ế l ượ ng-… Kinh tế lượng None 2
T ổ ng h ợ p các công th ứ c môn Kinh t ế … Kinh tế lượng None 5
Nh ậ n d ạ ng đ ề thi Kinh tế lượng
Kinh tế lượng None 7 đ ề tài nghiên c ứ u d ự giá vàng
Kinh tế lượng - AAA Class
14 validations in the determinants of the shadow economy And the final part will summarize all the results as well as present the limitations and directions for future research.
MAIN CONTENTS
Literature Review
The first studies in the area of the shadow economy defined the word in terms of the output of products and services (whether legal or illegal) not included in the official estimates of the gross domestic product in an effort to determine the size of the shadow economy (Smith, 1994) The shadow economy is defined by Schneider (1994) and Lubell (1991) as any economic activity that is not included in the computation of the gross national product Other scholars claim that the "unreported revenue from the legal creation of products and services in monetary exchanges or barter, so all economic activity which would ordinarily be taxed" is what they refer to as the
"underground economy" (Schneider and Enste, 2000, p 5).
The majority of the research on the underground economy uses Friedrich Schneider's studies' estimations of it as a dependent variable (2004, 2005; 2010) The widespread use of these estimations suggests that they are reliable In order to put this study's findings into perspective, Mai Hassan and Friedrich Schneider's study's most recent calculations of the extent of the underground economy were used for being one of the most recent estimations and have not been utilized in any previous studies (2016).
One of the foremost factors relating to the shadow economy that most literature articles mention is tax revenue and tax rate The higher overall tax burden and/or lower monitoring and enforcement, the stronger incentive for tax evasion and underreporting of wages (Schneider and Williams 2013, Hassan and Schneider 2016) The overall tax burden's distortion influences labor-leisure choices and may increase the labor supply in the shadow economy The motivation to lower the tax wedge and work in the shadow economy increases with the gap between total labor costs in the official sector
Kinh tế lượng None14 and after-tax earnings (from work) The overall tax burden and the social security burden/payments are both impacted by this tax wedge, making them important factors of the shadow economy's viability (Thomas 1992; Johnson, Kaufmann, and Zoido- Lobatón 1998a, b; Giles 1999a; Tanzi 1999; Schneider 2003, 2005; Dell’Anno 2007; Dell’Anno, Gomez-Antonio and Alanon Pardo 2007).
Many articles have indicated that there is a relationship between the underground economy and inflation rate Seigniorage earnings increase along with the rise of inflation As a result, both the tax rate and tax distortions can be reduced since the government no longer needs to impose high taxes in order to generate more revenue through seigniorage Lower taxes encourage formal sector activity as opposed to production for the illegal market Consumer price index has been used to calculate inflation in the majority of earlier studies (Erdinỗ, 2016; Gulzar, Junaid, & Haider, 2010; Schneider & Bajada, 2003).
The connection between unemployment and the size of the shadow economy is a topic of discussion There may be a negative relationship because an economic downturn would result in unemployment in both the formal and informal sectors The majority of previous research has used the unemployment rate as a proportion of the workforce to calculate unemployment Other criteria, particularly the degree of education, have an impact on the size of the underground economy (Gulzar et al., 2010; M Hassan & Schneider, 2016; Kanniainen, Pọkkửnen, & Schneider, 2004; Saafi, Farhat, & Haj Mohamed, 2015; Sarac, 2012; Savasan, 2003) What’s more, in an economic downturn, unemployment would occur in both the official and unofficial economies, meaning that a greater unemployment rate during the recession phase might indicate negative effects on both economic kinds.
According to literature, regulations, such as those governing the labor market or trade barriers, are another significant factor that limits people's freedom (of choice) in the formal economy They substantially raise labor costs in the official economy,giving people more of an incentive to work in the shadow sector: nations with higher levels of regulation typically have a higher percentage of the shadow sector in total
GDP The main factor affecting the burden placed on businesses and people, leading them to participate in the shadow economy, is enforcement, not the entire scope of legislation, which is typically not enforced (Johnson, Kaufmann, and Shleifer 1997; Johnson, Kaufmann, and Zoido-Lobatón 1998b; Friedman, Johnson, Kaufmann, and Zoido- Lobatón 2000; Kucera and Roncolato 2008; Schneider 2011; Hassan and Schneider 2016)
Another aspect that may be a key factor to the underground economy is the development of the official economy The lower the GDP growth, the higher the incentive to work in the shadow economy, ceteris paribus (Schneider and Williams 2013; Feld and Schneider 2010) But regarding the EU region's strong institutional standards and high level of governance, it is difficult for businesses and individuals to comply with economic regulations, therefore national GDP performance may be enhanced but also businesses are easily driven into the shadow economy.
Using the Internet has proven to have negative correlation with the growth of the shadow economy As more people use the internet, they’ll have the insight of drastic consequences of activities such as corruption or tax evasion As a result, awareness will be raised and people will take their own measures to alleviate and reduce the risks and sizes of such activities, leading to the reduction of the underground economy For instance, since the underground economy gives a strong foundation for corruption, reducing it will lead to the size decrease in the shadow economy (Elbahnasawy, 2014; Elgin, 2012; Goel, Nelson, & Naretta, 2012; Shrivastava & Bhattacherjee, 2014).
While there’s no direct link between population growth and the shadow economy itself, this factor is a key component to corruption, a very crucial aspect when it comes to measuring the shadow economy Therefore, the connection between population growth and the shadow economy is an indirect one As population growth develops, it fuels corruption more and from there increases the size of the shadow economy.
Theoretical framework
The causes and factors that drive the shadow economy are various and numerous. While the bulk of the literature has demonstrated a wide range of factors that influences and helps operate this kind of economy In this report, we would like to assess seven main factors, which act as driving forces of the shadow economy.
After a thorough process of research on the topic of shadow economy, we would like to propose the independent variables that may act as the driving forces as follows:
Inflation is a rise in prices, which can be translated as the decline of purchasing power over time The rate at which purchasing power drops can be reflected in the average price increase of a basket of selected goods and services over some period of time The correlation between inflation rate and the underground economy is negative, ceteris paribus Inflation rate is caculated as follow:
The unemployed are those who are out of work and who are actively looking for a job. The unemployment rate can be calculated by dividing the number of unemployed people by the total number in the labor force, then multiplying by 100 The correlation between unemployment rate and the underground economy is negative, ceteris paribus. Unemployment rate is caculated as follow:
This is the number of people using the Internet by whatever means of communication. For the sake of this report, we will only be addressing the number of internet users in the European Union The correlation between the number of internet users and the underground economy is negative, ceteris paribus.
Tax revenue rate is defined as the funds collected from taxes on income and profits; Social Security taxes or “contributions”; taxes levied on goods and services, generally categorized as “consumption taxes”; payroll taxes; taxes on the ownership and transfer of property; and other taxes The correlation between tax revenue and the underground economy is positive, ceteris paribus.
Population growth is the increase in the number of people in a population or dispersed group Due to the purpose of this report, only the population growth in the European Union will be assessed The correlation between population growth rate and the underground economy is positive, ceteris paribus.
The GDP growth rate measures the percentage change in real GDP (GDP adjusted for inflation) from one period to another, typically as a comparison between the most recent quarter or year and the previous one The correlation between GDP growth rate and the underground economy is positive, ceteris paribus GDP growth is caculated as follow:
The Index of Economic Freedom compares various jurisdictions based on factors like trade freedom, tax load, judicial efficacy, and more The correlation between economic freedom index and the underground economy is positive, ceteris paribus.
Empirical Model
Based on the above analysis and hypotheses, we decided to apply quantiative methods and least-squares estimation method OLS (Ordinary Least Squares) to analyze the econometric model of factors affecting European Underground Economy in period 2008-2021.
Based on previous studies, we selected independent variables from the affecting factors given in World Bank, The Heritage Foundation as the main sources and other official electric databases: GDP growth, CPI, Unemployment rate, Internet users, Tax revenue rate, Population growth, Index of economic freedom The definition of these variables is given below:
Shadow Economy Size (variable name SSE): Underground economy, also called shadow economy, is the transaction of goods or services not reported to the government and therefore beyond the reach of tax collectors and regulators The term may refer either to illegal activities or to ordinarily legal activities performed without the securing of required licenses and payment of taxes.
GDP growth (variable name GDPGR): The GDP growth rate compares the year- over-year (or quarterly) change in a country’s economic output to measure how fast an economy is growing
CPI (variable name CPI): The Consumer Price Index, or CPI, is a metric which measures inflation by calculating the price change for a basket of goods “Basket of goods”in this context refers to goods associated with the cost of living: transportation, food, medicine, energy, etc The CPI establishes the prices during a base year, and calculates the price increase or decrease of the same goods during a later year CPI is one of the primary metrics used to identify periods of inflation or deflation It can also be used to estimate the purchasing power of a country’s currency.
Unemployment rate (variable name UER): The unemployment rate is the percentage of people in the labour force who are unemployed Consequently, measuring the unemployment rate requires identifying who is in the labour force The labour force includes people who are either employed or unemployed.
Internet users (variable name IUR): Internet users are individuals who have used the Internet (from any location) in the last 3 months The Internet can be used via a computer, mobile phone, personal digital assistant, games machine, digital TV etc In the context of the survey on internet use within households, an internet user is defined as someone who has used the internet within the last three months, while a regular internet user is defined as someone who has used the internet at least once a week within the reference period of the survey (the first three months of the calendar year), regardless of where they do so.
Tax revenue rate (variable name TRR): Tax revenue is defined as the revenues collected from taxes on income and profits, social security contributions, taxes levied on goods and services, payroll taxes, taxes on the ownership and transfer of property, and other taxes Total tax revenue as a percentage of GDP indicates the share of a country's output that is collected by the government through taxes It can be regarded as one measure of the degree to which the government controls the economy's resources The tax burden is measured by taking the total tax revenues received as a percentage of GDP This indicator relates to government as a whole (all government levels) and is measured in million USD and percentage of GDP.
Population Growth (variable name POPG): Population growth refers to the increase in the number of individuals in a population in a particular year Population growth can be measured in two ways In general, the most reliable estimates often come from abundance data collected over many years Population abundance can be estimated from surveys or counts, and when repeated over several years, the trend (percentage change per year) in a population can be estimated A less direct way of estimating population growth is from life-history data Estimates of age of sexual maturity, birth rate, juvenile and adult survival rate, and maximum age can be compiled in a Leslie matrix or similar model, which can then be used to estimate the rate of increase.
Index of Economic Freedom (variable name IEF): The Index of Economic
Freedom is an annual index and ranking created in 1995 by The Heritage
Foundation and The Wall Street Journal to measure the degree of economic freedom in the world's nations.
3.3 Expected signs of variables and definitions:
1 (regression coefficient of GDP growth) is expected to be positive: Due to strict governance and high institutional quality in the EU region, the enforcement of economic regulation levied burden on firms and individuals, which enhances national GDP performance but simultaneously drives firms into the shadow economy.
2 (regression coefficient of CPI) is expected to be negative: Incomes from seigniorage (the profit made by government by issuing currency) rise when inflation rates rise Government no longer needs to tax as heavily in order to raise more money via seigniorage, which allows for a decrease in both the tax rate and tax distortions Lower taxes in turn promote activities in the formal sector as opposed to production in the black market
3 (regression coefficient of unemployment rate) is expected to be negative: An economic downturn would mean that unemployment exists in both official and unofficial economies, which means that higher unemployment rate in the recession phase can imply the downsize of both economic types.
4 (regression coefficient of internet users) is expected to be negative: Internet connects users sharing information about current affairs in daily life In addition, it spreads awareness among users about the shadow economy, which can cause corruption on the economy As the number of internet users grows, people are more thoughtful about the underground economy.
5 (regression coefficient of tax revenue rate) is expected to be positive: Since underground economy doesn’t pay taxes, it makes tax revenue rate lower Therefore, if tax revenue rate increases, the size of shadow economy also expands.
6 (regression coefficient of population growth) is expected to be positive: When the population grows, there is a likelihood that more people working in the shadow economy Thus, the size of the shadow economy enlarges.
7 (regression coefficient of index of economic freedom) is expected to be negative: People who are free to work together in a free market with institutions that uphold strong private property rights and where they are not subject to overly high taxes and restrictions feel less of a need to enter the shadow economy.
Data source
Variable Full variable name Unit Source
SSE Size of Shadow Economy % of GDP Worldbank
CPI Consumer Price Index % Worldbank
IUR Internet users Per 100 users Worldbank
POPG Population Growth Rate Annual % Worldbank
TRR Tax Revenue % of GDP Worldbank
UER Unemployment rate % of total labor force
The data set is panel data:
The data set in use is panel data To evaluate the impact of listed factors on the underground economy rate of 27 countries in Europe, we resorted to panel data with a time frame starting from 2008 to 2021.
It consists of 369 observations, including countries in the European Union. Differences between the development level of these countries will create a considerable variation in the data set, clearly showing the impact direction of the independent variables on the sub-variable.
Observing the data set, we realized there might be a linear relationship between the dependent variable SSE and seven independent variables Therefore, we decided to build the regression model in the form of a linear model.
Thus the model has the form of:
SSE: : Size of Shadow Economy
IEF : Index of Economic Freedom
: Regression coefficient : Estimated free coefficient When independent variables of GDPGR, CPI, UER, IUR, TRR, POPG, IEF equal 0, the average value of dependent variable SSE will be
: Estimated slope coefficient When independent variables of GDPGR, CPI, UER, IUR, TRR, POPG, IEF change by 1 unit (other factors remain unchanged), the average value of the dependent variable will change respectively by
Summary statistics and correlation of variables
Summary statistics: Before analyzing the collected data, we will bring in general description about the model and the parameters by using the command sum in STATA. This command reveals the Observations (Obs), Mean, Standard Deviation (Std Dev.) as well as Minimum (Min) and Maximum (Max) values of the variables.
The results is shown in the following table:
Table 3 Summary statistics of the regression model’s variables
+ SSE: The mean value of Shadow Economy Size in 28 countries in the period of
2008 to 2021 is 18.72656, the standard deviation is 7.034049, min value is 6.1 and max value is 32.93 (% of GDP)
+ GDPGR: The mean value of GDP Growth in 28 countries in the period of 2008 to
2021 is 1.406051, the standard deviation is 4.121146, min value is -14.83861 and max value is 25.1765 (%)
+ CPI: The mean value of Inflation rate (measured in CPI) in 28 countries in the period of 2008 to 2021 is 1.779284, the standard deviation is 1.973599, min value is-4.478103 and max value is 15.40232
+ UER: The mean value of unemployment rate in 28 countries in the period of 2008 to
2021 is 8.641944, the standard deviation is 4.496867, min value is 2.01 and max value is 27.47 (% of labor force)
+ IUR: The mean value of the number of internet users in 28 countries in the period of
2008 to 2021 is 76.29486, the standard deviation is 13.86454, min value is 32.42 and max value is 98.82242 (% of population)
+ TRR: The mean value of the tax revenue rate in 28 countries in the period of 2008 to
2021 is 21.34963, the standard deviation is 4.806206, min 10.66701 value is and max value is 46.04608 (% of GDP)
+ POPG: The mean value of population growth rate in 28 countries in the period of
2008 to 2021 is 0.2103647, the standard deviation is 0.8368557, min value is -3.742377 and max value is 3.931356 (%)
+ IEF: The mean value of Economic freedom index in 28 countries in the period of
2008 to 2021 is 69.80212, the standard deviation is 5.647661, min value is 53.2 and max value is 82 (%)
Correlation of variables: To identify the correlation among the six variables of the model, we used command corrá the results are illustrated as following:
Table 4 Correlation coefficients among variables using command [corr]
+ GDPGR has a very low correlation coefficient of (+0.0117), and the plus sign indicates a positive impact it has on SSE
+ CPI has a very low correlation coefficient of (-0.0302), and the minus sign indicates a negative impact it has on SSE
+ UER has a low correlation coefficient of (+0.0410), and the plus sign indicates a positive impact it has on SSE
+ IUR has a high correlation coefficient of (-0.3681), and the minus sign indicates a negative impact it has on SSE
+ TRR has a relatively high correlation coefficient of (+0.2221), and the plus sign indicates a positive impact it has on SSE
+ POPG has a relatively high correlation coefficient of (+0.2094), and the plus sign indicates a positive impact it has on SSE
+ IEF has a relatively high correlation coefficient of (-0.2032), and the minus sign indicates a negative impact it has on SSE
Among the independent variables, IUR is the greatest factor to have impact on
SSE with a correlation coefficient of (-0.3681) Additionally, TRR also has a great impact on SSE with a second highest correlation coefficient of (+0.2221) Whereas,the correlation coefficient that GDPGR regarding is the smallest, which suggests an insignificant effect GPD growth have on SSE.
Estimation results and diagnostic tests
5.1 Analysis of estimated regression results:
Using the reg command ([reg SSE GDPGR CPI UER IUR TRRR POPG IEF]) to run the regression model, the results are depicted as follow:
We have the sample regression function:
According to the results of running regression using OLS method on STATA software, we have a sample regression function (SRF) as follows:
5.1.2 Testing the appropriateness of the regression model
Use P-value method with P-value acquired in Table … and � = 5%
If [Prob>F] is less than � = 5%, we reject �0 and accept �1, which means the regression model is appropriate
According to the regression result:
Therefore, at � = 5%, the regression model is appropriate.
Conclusion: The model is statistically significant at � = 5%
With the sample regression function:
+ = 44.00755 means that when the value of independent variables equals 0, shadow economy size equals 44.00755.
+ = 0.1606299 means that when GDP growth rate increase by 1%, shadow economy size will increase approximately by 16.06% (in case other factors remain unchanged). + = - 0.4040678 means that when CPI increase by 1%, shadow economy size will decrease approximately by 40.04% (in case other factors remain unchanged). + = - 0.1482589 means that when unemployment rate increase by 1%, shadow economy size will decrease approximately by 14.82% (in case other factors remain unchanged).
+ = - 0.2805695 means that when internet users increase by 100, shadow economy size will decrease approximately by 28.06% (in case other factors remain unchanged). + = 0.3609066 means that when tax revenue rate increase by 1%, shadow economy size will increase approximately by 36.09% (in case other factors remain unchanged). + = means that when population growth rate increase by 1%, shadow economy size will increase approximately by 242.19% (in case other factors remain unchanged). + = - means that when index of economic freedom increase by 1%, shadow economy size will decrease approximately by 14.61% (in case other factors remain unchanged).
R-squared = 0.3436 shows that the sample regression function is relatively appropriate This means that the independent variables can explain 34.36 % in the change of the value of the dependent variable, the rest are explained by are others.
5.1.5 Testing the statistical significance of independent variables
With P-value acquired in Tablem… and � = 5%
+ GDPGR: P-value < � (0.035 < 0.05), reject �0, thus the coefficient is statistically significant, which means GDP growth rate has an impact on shadow economy size.
+ CPI: P-value < � (0.020 < 0.05), reject �0, thus the coefficient is statistically significant, which means inflation rate has an impact on shadow economy size.
+ UER: P-value > � (0.114 > 0.05), accept �0, thus the coefficient is statistically insignificant, which means unemployment rate has little impact on shadow economy size.
+ IUR: P-value < � (0.000 < 0.05), reject �0, thus the coefficient is statistically significant, which means the number of internet users has an impact on shadow economy size.
+ TRR: P-value < � (0.000 < 0.05), reject �0, thus the coefficient is statistically significant, which means tax revenue rate has an impact on shadow economy size.
+ POPG: P-value < � (0.000 < 0.05), reject �0, thus the coefficient is statistically significant, which means population growth rate has an impact on shadow economy size.
+ IEF: P-value < � (0.019 < 0.05), reject �0, thus the coefficient is statistically significant, which means economic freedom index has an impact on shadow economy size.
Conclusion: At � = 5%, almost all of the independent variables (6/7: GDPGR, CPI,
IUR, TRR, POPG, IEF) are statistically significant.
5.2 Testing for violations of classical linear regression model assumptions
Using the Variance Inflation Factor (VIF) method to detect whether the model has multicollinearity or not If existing at least one value of VIF greater than 10, the model contracts this defect.
With the vif command in STATA, we have the result as follow:
Table 6 Results for detection of multicollinearity using command [VIF]
All VIF value of independent variables are less than 10.
Conclusion: The model does not have multicollinearity
Using the estat hettest command (Breusch–Pagan test) in STATA, we can detect whether model incurs heteroskedasticity or not The result we got is shown as the following:
Model has P-value = 0.4733 >0.05 => do not reject H0
Conclusion: At � = 5%, the model is not heteroskedastic
We used the Arellano Bond test to detect whether the model has auto- correlation or not Using the abar, lags(13) command (with 13 being the number of year lags) in STATA, we have collected the result as follow:
Conclusion: At � = 5%, the model has first, second, third, fourth, fifth, sixth, seventh, eighth, ninth, tenth, eleventh and twelfth order auto-correlation.
We used the Ramsey RESET test to find out wether the model has omitted variables or not Using the command quiet reg followed by ovtest in STATA, this is the result we have collected:
Conclusion: At � = 5%, model has omitted variables.
Brief explanation: Due to the nature of black market, our team encountered several difficulties in finding precise data when looking for factors determining underground economy as we could hardly find sufficient official publications of the figures for the factors In addition, we also faced the puzzle of economic knowledge insufficiency and short timeframe Therefore, the group has not found all the needed explanatory variables in the model and our model has obmitted variable bias.
5.3 Remedies for violations of classical linear regression model assumptions
In the previous part, using the Arellano Bond and Ramsey RESET test, we have detected that the model violated two classical linear regression model assumptions The two violations are auto-correlation and omitted variables Thus in this part we will be providing the remedies for the aforementioned violations.
5.3.1 Remedy for auto-correlation violation
Regarding the research’s limitation, we only performed the first-difference transformation to solve the incurrence of first-order auto-correlation.
Step 1: Generating first-difference variables
Applying command ([gen dvarname = varname – varname[_n-1]]) for the dependent variable and all independent variables, we can get the new variable list as follows: dSSE, dGDPG, dCPI, dIUR, dIUR, dTRR, dPOPG and dIEF.
Step 2: Running the new regression model
By using command ([reg dSSE dCPI dGDPGR dUER dIUR dTRR dPOPG dIEF]), we got the results shown in the table below:
Table 7 Estimated regression results after using first-difference transformation
Step 3: Using Arellano-Bond test to detect the incurrence of auto-correlation
Using command [abar, lags(1)], we obtained the following results:
By applying first-difference transformation, we have managed to remove the first- order auto-correlation of the model (P-value = 0.7742 > 0.05)
However, in the process of applying the transformation, three out of seven of the regression variable (dGPDG, dCPI, dUER) are now not statistically significant at � 5%.
Method 2: Inclusion of first-order lagged dependent variable
Step 1: Running regression model with the first-order lagged variable sse L1. inluded
Using the command [reg SSE L1 SSE GDPGR CPI UER IUR TRR POPG IEF] we obtain the result as follow:
Table 8 Estimated regression results after including the first-lagged dependent variable
Step 2: Using Arellano-Bond test to detect the incurrence of auto-correlation
Using command [abar, lags(9)], we obtained the following results:
With this method, we eliminated the third, fourth, fifth, sixth, eighth, ninth, tenth, twelfth order auto-correlation In the process, we also reduced the number of observation, down to 343 (a 26 observation loss regarding the original model) The method also generated five out seven statically significant regression coefficients at �
After applying the two methods of First-difference transformation and
Inclusion of first-order lagged dependent variable, we were only able to mitigate the effect of auto-correlation, unfortunately not completely solving the problem.
5.3.2 Remedy for Omitted Variable violation
Step 1: Model transformation to lin-log form by generating new logarithmic variables
Using the ([gen lvarname=ln(varname)]) command in STATA, we generated now logarithmic variables.
Step 2: Run the newly transformed regression model
Using command [reg SSE lGDPGR lCPI lUER lIUR lPOPG lIEF lTRR] we obtained the result below:
Table 9 Estimated regression results after the model transformation
Using command [ovtest], we obtained the following results:
Model P-value = 0.2248 > 0.05 => The model has no omitted value bias
With this method, we eliminated the obmitted variable bias In the process, we also reduced the number of observation, down to 162 The method also generated four out seven statically significant regression coefficients at � = 5%.
CONCLUSION AND POLICY IMPLICATIONS
The informal economy consists of unregistered economic activities that are not regulated by the government and are not recorded Despite providing economic value,the informal economy is not included in a country's GDP since it is difficult to measure The informal economy renders official statistics such as unemployment, internet users, and an index of economic freedom Therefore, policies formulated based on inaccurate information may be ineffective.
A variety of policies should be implemented, targeting the most significant variables in each country The shadow economy's scale (using any estimation methods) is substantially and negatively connected to per capita income, and more effective institutions are essential to accomplishing development objectives Moreover, improving tax administration, reducing regulatory burdens, and enhancing transparency would reduce incentives for informal activities driven by "exit" factors, whereas enhancing the functioning of the labor market and promoting human capital assist in addressing informality resulting from "exclusion" factors.
Actions designed to increase income can also assist reduce the shadow economy. The potential for development in Europe's tax administration varies, but most nations have difficulties with poor automation of procedures, organizational structure, and operational effectiveness Examples of practical policy actions include:
Improving registration, auditing, and collection to increase tax compliance. Registration can be enhanced by easing information sharing across government agencies; for instance, in most EU nations, businesses and employees have a single company ID for social security, unemployment, and tax authorities The tax base can be enlarged by removing current exemptions that skew the tax base.
Computerizing and automating processes Minimizing interactions between tax authorities and taxpayers tends to reduce bureaucracy Simplifying tax and social benefits systems will lower tax compliance costs, if not tax rates.
Increasing electronic payment use This can assist in increasing tax revenues and reducing VAT fraud Several nations have recently mandated that firms record payments and money transfers using fiscal instruments According to Schneider andKearney, boosting electronic payments by an average of 10 percent per year for at least four consecutive years can lower the shadow economy by as much as 5 percent.
Promoting electronic payments and limiting the use of cash would likely help with shadow activities in which one party (typically a consumer) does not benefit from not reporting the transaction (and may not even be aware that they are contributing to the expansion of the shadow economy through the cash payment), when both parties to a transaction gain by non-reporting, the effect of promoting electronic payments may be diminished.
Labor market reforms and human capital development
In nations with accelerated migration rates and where the shadow economy may serve as a social safety net, policy initiatives should enhance incentives for informal workers to transition into the formal sector When so-called “exclusion" reasons predominantly drive informal activities, a singular emphasis on enforcement and compliance may result in informal employees finding employment overseas and the demise of shadow enterprises In such a situation, increasing private-sector job creation and fostering skill development would assist in bringing enterprises and people out of the shadows and promoting more equitable growth.
The job-search capabilities and earnings potential of informal employees will be enhanced by policy measures targeted at improving human capital Included among the pertinent labor market and education policies are:
Enhancing employment and termination flexibility (e.g., labor market changes in Slovakia) in the situation of too restrictive labor laws while enforcing such rules elsewhere ensures a fair playing field and encourages lawful conduct
Increasing enforcement and surveillance (e.g., enforced obligation to register all new workers in Bulgaria)
Increasing labor market inclusion through creating and executing individualized employment and training interventions for populations most at risk of social exclusion (e.g., young people)
Creating a conducive job climate for returning migrants by providing them with specialized training and recognizing their acquired practical skills
Increasing the relevance of professional and vocational education and training and promoting internal cross-sector mobility
Improving the effectiveness of monies provided for education by prioritizing, screening, and monitoring education programs more effectively.
Through researching and testing with the help of the STATA software, our group has demonstrated the factors affecting the growth of the shadow economy in 27 European Union countries from
2008 to 2021 Observations have been qualified and deeply delved into so that we could optimize assessments over factors, namely
GDPGR, CPI, UER, IUR, TRR, POPG, and IEF In this study, we used data from the World Bank and the Heritage Foundation and then applied
OLS to investigate the topic
From the results, the size of the shadow economy has a negative relationship with CPI, unemployment rate, internet users, and the index of economic freedom At the same time, the informal economy is positively affected by GDP growth, tax revenue, and population growth rate.
In conclusion, based on the conclusions drawn from the above analysis, the research team has also made some recommendations and the right policies and measures to contribute to the downsizing of the underground economy in the European Union in the future.
Our group hopes the above essay will help us have an objective, comprehensive view and better understand the growth of the shadow economy in this day and age
However, our report still has some significant limitations, including the failure to solve the auto-correlation for all orders using the first method (Method 1: First- difference transformation) that we applied in section 5.3; and the unsuccessful attempt to eliminate auto-correlation for all orders at once (Method 2: Inclusion of first-order lagged dependent variable).
Due to the lack of practical experience and limited knowledge, our group report may have many shortcomings, the model is not high, and the data is still inconsistent This requires team members to continue researching and reading articles and documents related to econometrics to enhance our knowledge This is a vital subject with very high applicability in reports and future work Since this is the first time the team has run an econometric model on its own, we have not practiced much in reality, so we look forward to receiving your comments and suggestions to improve our report We sincerely thank Ph.D Vu Thi Phuong Mai for your help completing our report to the fullest
Aziz N Berdiev, James W Saunoris and Friedrich Schneider (2018.) Give MeLiberty, or I Will Produce Underground In JSTOR Retrieved from https://www.jstor.org/stable/26633581
B Kelmanson, K Kirabaeva, L Medina, B Mircheva and J Weiss (2019) ‘IMF
Working Paper: Explaining the shadow economy in Europe: size, causes and policy options
Brindusa Mihaela and Raluca Irina (2016) ‘An Analysis of the Shadow Economy in EU countries
Blunch N.H., Canagarajah S and Raju D (2001) ‘The informal sector revisited: A synthesis across space and time’, World Bank Social Protection Discussion Papers, 119.
Friedrich Schneider (2018) ‘IMF Working Paper: Shadow Economies Around the
World: What Did We Learn Over the Last 20 Years?’
Friedrich Schneider, Vesa Kanniainen, and Jenni Paakkonen (2004) ‘Determinants of
Shadow Economy: Theory and Evidence’
Econlib (n.d.) Scarcity, Econlib website, accessed 15 July 2022
Economy and Economic Development In JSTOR Retrieved from https://www.jstor.org/stable/27720402
OECD (2016), OECD Reviews of Labour Market and Social Policies: Latvia 2016, OECD Publishing, Paris.
Leandro Medina and Rafael La Porta and Andrei Shleifer (2008) The Unofficial Juzhong Zhuang, Emmanuel de Dios, and Anneli Lagman-Martin (2010) Governance and Institutional Quality and the Links with Economic Growth and Income Inequality: With Special Reference to Developing Asia In ADB Retrieved from https://www.adb.org/sites/default/files/publication/28404/economics-wp193.pdf Rajeev Goel, James W Saunoris, Friedrich Georg Schneider (2017) GROWTH IN THE SHADOWS: EFFECT OF THE SHADOW ECONOMY ON U.S ECONOMIC GROWTH OVER MORE THAN A CENTURY In Contemporary Economic Policy Retrieved Schneider M.F and Enste D (2002) Hiding in the shadows: the growth of the underground economy International Monetary Fund.
H ướ ng d ẫ n t ự h ọ c môn Kinh t ế l ượ ng-… Kinh tế lượng None 2
Tổng hợp các công th ứ c môn Kinh t ế … Kinh tế lượng None 5
Nh ậ n d ạ ng đ ề thi Kinh tế lượng
Kinh tế lượng None 7 đ ề tài nghiên c ứ u d ự giá vàng