Use the empirical data to analysis the gender has a strong effect on wages growth, homework help

User Generated

ebpxlfuv

Economics

Description

we have to use methodology to analysis the relationship between wages (column B) and male/female wage ratio(column F), we pick the regression analysis, we want multiple linear regression excels and tables to show the relationship.

wages growth=f [ male/female], unemployment, population growth, male/female wage, race, GDP per capital

the 30-year data for the variables(C,D,E,F,G) to affect the wage growth.

we provide a model paper to talk about immigration and unemployment, we just need the table on model paper's 6 and 7 pages and little bit data analysis.

Unformatted Attachment Preview

Year 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 Median Wage in USD 22.259 23.457 24.635 25.872 27.559 28.680 29.017 29.640 30.404 31.522 33.456 34.941 36.477 38.383 40.201 41.446 41.728 41.911 42.823 43.785 45.770 47.599 49.614 49.671 49.158 48.691 49.423 50.396 52.937 53.013 GDP Per Capita Population growth (annual %) 18.232 0,9 19.078 0,9 20.063 0,9 21.442 0,9 22.879 0,9 23.954 1,13 24.405 1,336 25.493 1,387 26.465 1,319 27.777 1,226 28.782 1,191 30.068 1,163 31.573 1,204 32.949 1,166 34.621 1,148 36.450 1,113 37.274 0,99 38.166 0,928 39.677 0,859 41.922 0,925 44.308 0,922 46.437 0,964 48.062 0,951 48.401 0,946 47.002 0,877 48.374 0,836 49.781 0,764 51.457 0,762 52.705 0,7 54.502 0,8 Unempolyment Rate 7,20% 7,00% 6,20% 5,50% 5,30% 5,60% 6,80% 7,50% 6,90% 6,10% 5,60% 5,40% 4,90% 4,50% 4,20% 4,00% 4,70% 5,80% 6,00% 5,50% 5,10% 4,60% 4,60% 5,80% 9,30% 9,60% 8,90% 8,10% 7,40% 6,20% Female/male wage 68,10% 69,50% 69,80% 70,20% 70,10% 71,90% 74,20% 75,80% 77,10% 76,40% 75,50% 75,00% 74,40% 76,30% 76,50% 76,90% 76,40% 77,90% 79,40% 80,40% 81,00% 80,80% 80,20% 79,90% 80,20% 81,20% 82,20% 80,90% Africa America/ White Wage 90% 90% 90% 90% 90% 87% 87% 87% 87% 85% 86% 85% 85% 86% 85% 86% 87% 86% 87% 86% 84% 85% 85% 85% 87% 87% 85% 84% women/men bechlor's degree or high 72% 74% 75% 76% 77% 76% 75% 75% 75% 76% 74% 74% 74% 74% 75% 76% 75% 75% 74% 73% 74% 75% 73% 75% 76% Group Project Globalization and the US: Immigration and Unemployment in the US Avenger-CBM600-Page1 Introdution Key Word: Unemployment Rate, Immigration, Multiple Linear, and Regression Model The primary purpose of this report is to determine the relationship of immigration and unemployment in the United States. First of all, we establish the hypothesis that immigration has a strong impact on the unemployment in the United States. Besides focusing on the immigration, we are also going to show the other elements that affect unemployment to reveal a completed concept of unemployment. With the aim of providing a professional report, all the analyses and conclusions we will make in this report are all based on accurate statistics from government reports and websites. The three components of the main body of the report are shown as follows:  Introducing the hypothesis and methodology we will use.  Introducing the variables that effect unemployment  The trend of immigration and unemployment in the latest thirty years in the U.S  Using multiple—linear regression model to analyze how the variables affect unemployment, and determine which the most significant variable is. We are about to conclude the relationship between the immigration and unemployment and determine that immigration has a positive or negative impact on unemployment. Last but not least, we will present some recommendations according to the conclusion. If immigration brings a positive impact on unemployment, we will suggest that government should encourage immigration and establish attractive laws and regulations to welcome foreigners. On the other hand, if immigration has a negative impact on unemployment, the suggestions would be how to restrict immigration to provide more career opportunities to native residents. Findings Highlight  U.S. Monthly Unemployment Rate, through Jan. 2005-Oct. 2015 are 16.5%, 15.3%, 15.7%, 18.7%, 24.3%, 25.9%, 24.4%, 24.1%, 22.9%, 19.5%, and 17.2%. The unemployment rates from 2009 to 2012 are highlighted since they are all above 20%  During the recession from 2009 to 2011, the unemployment rate of people who attained low Avenger-CBM600-Page2 education was still much higher than the people who had high education level.  The unemployment rate of immigrants was higher than that of Native-born until 2004. And the unemployment rate of the natives became lower than immigrants again during the period of 2009 to 2012.  A noticeable increasing of the unemployment rate of both the natives and the immigrants can be noticed in 2008, and it became more aggressive in the year 2009.  The unemployment rates of the natives from age 25-44 were slightly higher than those of immigrants during 2010 to 2012, whereas the rates of all natives were actually lower than all immigrants. Hypotheses Before any analysis is launched based on the existing statistics, we can make a conclusion right behind the previous literature review that the factors may contribute to the changes in unemployment rate in the U.S. are based on the following elements: CPI, which is The Consumer Price Index, is a measure of the average change over time in the prices paid by urban consumers for a market basket of consumer goods and services. In common view, the CPI may oppositely change with the unemployment rate, which means as the raise of unemployment rate, the CPI may likely fall because firstly it comes with more difficulty for employed workers to ask higher wage due to the high unemployment rate. For another, the lower manufacturing output might be caused due to the higher unemployment in the picture of economy. Education levels, according to the unemployment theory, people who have higher education level are more employable since they carry stronger competition and capacity comparing with those who had only little education. In other word, in the whole labor force market, higheducated people have less possibility to take lower end jobs that might increase unemployment rate under the situation of competition. Age, as survey shows, people among 16-24 years old have significant association with the status of out-of-labor-force base on the understanding of socioeconomic mental health disparities. (Mossakowski, 2009) Avenger-CBM600-Page3 Immigrants Admitted is another factor that affect directly or indirectly the unemployment rate of a country. As unemployment rate is usually a efficient index to evaluate the economic condition since good economic condition may provide more available job opportunities to the labor market. Otherwise, poor economic condition will cause higher unemployment. In the meantime, a country’s good economic condition will attract mire immigrants to the country, which could be potentially regarded as a positive relationship with unemployment rate. GDP Per Capita, as one the most important economic indicators, is gross domestic product divided by midyear population. The unemployment rate is an issue of the importance that involved in the employment, which is a dominant factor to affect the domestic income that closely related to the GDP per Capita. We assume that all the variables above as a whole as well as individual ones have direct relationship with the unemployment rate. And the analysis will find out which one of the variables has the most significant impacts on the unemployment. Methodology The analysis adopts the 30-year data from 1985-2014 for the variables we choose. The data before 1985 is not chosen because there is the lack and discontinuity for some of them, such as the civilian labor force attained by education. All the data are from three sources, United States Census Bureau (USCB), Bureau of Labor Statistics (BLS), and the World Bank (WB). Among them, the unemployment rate and the civilian labor force by age are from BLS, the data of immigrants admitted is from USCB, and the CPI and GDP per capita are from WB. Since there is only data for the labor force attained by education from 1992 to 2014 on BLS, the data before 1992 is from USCB. As mentioned above, the unemployment rate is the annual rate of the unemployment from 1985-2014. The variable immigration means the number of immigrants admitted by the U.S. government each year. We use the number of the civilian labor force that have high school and lower education to symbolize the variable education. Same as variable age, we choose the number of the civilian labor by age from 16 to 24. As for CPI and GDP per capita, since they are general economic indicator, we use the data directly from WB as the according variables. In order to determine if the variables relate to the unemployment, we use one of the statistical analysis methods, multiple linear regression analysis, to build the mathematical model. Avenger-CBM600-Page4 In the regression model, the unemployment rate is dependent variable and the factors affecting the unemployment are independent variables. The multiple linear regression analysis is a statistical method that tries to find if there are the correlations between the dependent variable and the independent variables as a whole as well as individuals. It can be expressed simply as: Y = b0 + b1*X1 + b2*X2 + b3*X3···· + bn*Xn If there is a certain correlation between the dependent and independent variables, the regression model will determine the coefficient that best suit for the above equation. Literature Review We have read through several articles and reports about unemployment. Unemployment is usually defined as the amount of people who are willing to work but cannot find a job, and it is essential to understand how unemployment rate can be presented by calculation. The unemployment rate is defined as the proportion of the citizens who are sixteen years and older in the United States who out of work but are actually looking for a position (Frumkin, 1998). However, people who are nursing homes and jails, and serving the army are not included in the labor force. The unemployment is Expressed as a percentage, by dividing the number of unemployed workers by the total labor force, and multiplying it by 100%. Unemployment also comes in different varieties, such as frictional, structural and seasonal. Frictional unemployment is when workers leave their jobs to find better ones. It usually occurs when workers want to find better opportunities to go on interviews before they start their new jobs. Structural unemployment is defined as the mismatch between jobs and skills. And seasonal unemployment only occurs where there is a limited need for a type of work to be performance during a particular period during the year based on factors like deadlines or climate. We also have read some relevant articles, which explain the factors contribute to unemployment. First factor is location, which has been shown on a larger scale that unemployment rates are dramatically different in urban and rural areas (Aragon, 2003, Hargrett, 1965, Klasen and Woolard, 1999, Taylor and Bradley, 1997). Second, mobility also affects unemployment to some extent; for example, immobility causes high unemployment because Avenger-CBM600-Page5 many positions are not available so that people will be unemployed in a long time. The third factor is education. There is a negative correlation between education and unemployment. The people who have received higher education or more professional skills are less likely to be unemployed than the people with less education and skills. Last factor is wage; especially minimum wage has many drastic effects on the labor market and unemployment rates (C. Campbell and R. Campbell, 1969). When minimum wage laws increase, unemployment increases because if labor costs are higher than they planned so that they will try to limit the number of employees to control their expenses. DATA analyze Regression Model Analysis After running the multiple linear regression analysis, we find that there does exist certain relationships between the unemployment rate and the variables we choose. We have the output result from the first table shown as below. (Please see the detailed data in appendix 1 and 2) SUMMARY OUTPUT Regression Statistics Multiple R 0.8636511 R Square 0.7458932 Adjusted R Square0.6929543 Standard Error 0.0081746 Observations 30 From the above results, the variables we choose as a whole have a high correlation with the unemployment rate, because the Multiple R is 86.4%, and the R Square is 74.6%, which means that the dependent variable, unemployment rate, can be well related to and explained by the independent variables as a whole. Avenger-CBM600-Page6 However, the correlation between unemployment rate and the variables as a whole does not mean that it is still true between the dependent variable and the individual variables. In order to determine the individual relationships between the variables, we need to use other tables from the regression analysis. The following table shows the results of relationships between the individual independent variables and the dependent variable. Coefficients Intercept -0.0522495 Immigration(thousand) -3.13E-06 Lower Educatoin(Labor force) 2.451E-06 age(16-24,Labor force) -7.008E-06 CPI 0.0023268 GDP per capita -7.164E-06 P-value 0.655052 0.6550885 5.285E-07 0.0806922 0.0031095 0.0067551 The p-value shows the probability of obtaining a result equal to or “more extreme” than what was actually observed. It means how significant each variable is. We assume that 0.05 is our significance level. So, the variable with p-value smaller than 0.05 is considered as the significant one that has impacts on the unemployment rates. In the above table, the variables of lower education, CPI, and GDP per capita are all significant variables. Since the p-value of the lower education is 5.285E-7, which is the smallest among the three variables, the lower education variable has the most possibility affecting the unemployment rate. And the p-values of CPI and GDP per capita are 0.0031 and 0.0068, respectively. These two variables are also significant variables that have high correlation with the dependent variable. However, the variable of immigrants admitted is not related to the unemployment rate based on the regression analysis, which is not as what we think it should be at the beginning of this paper. Actually, it is the least significant factor that affects the unemployment rates. Results Based on the above analysis, we have the results that the independent variables that we choose to build this mathematical model as a whole have high correlation with the unemployment rate from year 1985 to 2014. Among these independent variables, the number of low education labor force is the most significant factor that has impacts on the unemployment, Avenger-CBM600-Page7 followed by the variables of CPI and GDP per capita. Since the low education and CPI have the positive coefficients according to the above table, they have direct relationship with the unemployment rate, which means that the higher the two variables are, the higher the unemployment rates. We think that this result is not difficult to understand. According to the research we read, people with bachelor degree or above is usually much easier to find and hold the jobs than those with lower education. Thus, the unemployment rates tend to be high if there are more low-educated workers. The consumer price index (CPI) measures changes in the price level of a market basket of consumer goods and services purchased by households. It has direct relationship with Inflation rate which actually reflect how a country’s economy is. A high inflation rate usually means the economy is not good, which leads to unemployment. Thus, it is understandable that CPI has a direct relationship with the unemployment rate. As for the GDP per capita, it is a measure of the total output of a country that takes the gross domestic product (GDP) and divides it by the number of people in the country. An increase in GDP per capita means growth in the economy. This explains the result of the relationship between the unemployment rate and GDP per capita. As showed above in the table, the coefficient of the variable GDP per capita is negative, which means a higher GDP per capita-good economy-will reduce the unemployment rate. Among the independent variables, immigrants and the young labor force are not the significant ones. Our results show that the variable of immigrants admitted will have the inverse relationship with the unemployment rate if it is the significant factor, since the coefficient is 3.13E-6. This result is actually same as the literature we read (Frumkin, 1998). The variable of young age labor force shows an interesting result. Its p-value is 0.00806922, and based on our preset significance level, it is not considered as a significant factor. However, if we set the significance level at 0.1 which is usually acceptable, the result will be different. Under this assumption, it will be a significant variable, and it will affect the unemployment rate inversely because the coefficient is negative. When the number of young age labor force increases, the unemployment rate is reduced. This is contradicted to what we have researched and the most people’s notion because the young workers are much easier to lose jobs compared to the primary age workers. We think the reason for this contradictory may be from the data we choose. For the young age labor force, we choose to use the data of labor force from age 16 to Avenger-CBM600-Page8 24. The age span may be too long. If we use the data from age 16 to 18, the result probably will be different. The college students are included in this age group of 16 to 24; same does those just graduates from university. This may be another reason considering the fact that education is a significant factor that affects the unemployment rate the most. Although the independent variables we use have relationships with the unemployment rate, they can be used to approximate the rate in the period of 1985 to 2014 only. It may be inappropriate to use these data for the period before 1985 or after 2014. And there are other factors may have impacts on the unemployment rate as well. We hope the relationships we found in this paper could provide some when forecasting the unemployment rate and making related policy decisions. Avenger-CBM600-Page9 Policy recommendations  Attracting high–skilled and well–education immigrants, graduates, and entrepreneurs For a long time, the strict immigration system in the United States has made it really difficult to attract the brightest talents. Many intelligent people choose to leave because they have to wait for years or even decades to get a green card before they start to contribute to America. However, U.S has cultivated large majority of talented students due to its outstanding education system. It will be beneficial for us if we retain the talented students we educate before they leave, especially the most talented students in mathematics, engineering, and technology, who will bring benefits to the development of science. It is helpful to extend the period of internship and on—job—training for the graduates from U.S universities, which makes them realize United States is an ideal country to make the most of their talent and knowledge. Another recommendation is to make it more possible for talented people to have portable jobs, allowing them to accept promotions or start new companies when they are waiting for a green card, which stimulates them to exert more efforts into their career paths in America. Nevertheless, the extension would cause the loss the jobs of native residents.  Reducing unemployment without causing an inflation There is a positive correlation between CPI and unemployment. CPI is used as a tool to measure the level of inflation in an economy. Therefore, reducing the inflation will be helpful to reduce unemployment. First of all, reducing the money supply by enacting policies will transfer money from investors ‘pockets to government, which can significantly control inflation. Second, increasing reserve requirement can be helpful to require bank to have more money and to have less money to lend to customers. So that customers have less money to spend and the inflation will be controlled.  Reducing Unemployment by increasing GDP There is a negative correlation between GDP and unemployment. An increasing GDP means the economy of the society is moving forward, which includes the decline of unemployment rate. For example, raising minimum wage will increase job growth, rising profits and U.S GDP because it increases demand by putting more money into people’s hands. Avenger-CBM600-Page10 Conclusion Throughout structure of the whole article, we firstly introduced the subject and the background investigation of unemployment - the basic profile of immigration, including immigrant rate of nearly 30 years, as well as the unemployment rate. Then we have had a literature review to obtain some inspirations for investigation below. Next, we launched a hypothesis by listing five variables that probably affect the likelihood of the US unemployment rate with analysis of each one, explaining why they have a direct or indirect impact on the unemployment rate. Then we thus introduced a linear regression model to prove our hypothesis. By analyzing the data and models, we have come to the conclusion that class of education has the greatest impact on the changes of unemployment rate in the U.S.- the lower the education level, the higher unemployment rate. Those results based on the linear regression model above might have further functions and enlightenments for the future political improvement for the United States. The price index regulation is used to adjust the price level of a nation in order to balance the overall rate of inflation in the economy and go further step to optimize the output and inputs. The improvement should aim on education level nationwide especially on the immigration policy. According to the previous analysis, the government would address stronger rights of competency on making efforts to attract growing number of immigrants who can be defined as needed personnel. Avenger-CBM600-Page11 Reference Adler, W. (1996) Land of Opportunity: One Family's Quest for the American Dream in the Age of Crack. Retrieved from https://books.google.com Aragon, Yves, et al. 2003. “Explaining the Pattern of Regional Unemployment: the Midi-Pyrenees Region.” Papers in Regional Science 82: The Case of 155-174. Baeder, J. (2012, October 22) Why U.S Schools Are Simply the Best. Education Week. Retrieved from http://blogs.edweek.org Campbell, Colin and Rosemary Campbell. 1969. “State Minimum Wage Laws as a Cause of Unemployment.” Southern Economic Journal 35:323-32. Frumkin, N. (1998). Tracking America’s economy. New York: M.E. Sharpe. Mazzarol, T. (2014, December 29) 6 Ways Governments can Encourage Entrepreneurship. Agenda. Retrieved from https://agenda.weforum.org Mossakowski, K. N., PhD. (2009). The influence of past unemployment duration on symptoms of depression among young women and men in the united states. American Journal of Public Health, 99(10), 1826-32. The Saylor Foundation. "Unemployment Rate." pp. 1 [1] Retrieved 20 June 2012 Tong, C. H., Tong, L., & Tong, J. E. (2012). High unemployment in the United States: Causes and solutions. Competition Forum, 10(2), 74-79. Avenger-CBM600-Page12 Appendix 1 Raw Data Collection for Regression Model and Analysis time 1985 1986 1987 1988 1989 1990 1991 1992 1993 1994 1995 1996 1997 1998 1999 2000 2001 2002 2003 2004 2005 2006 2007 2008 2009 2010 2011 2012 2013 2014 Unemplo Immigrati yment on(thous rate and) 7.2% 570 7.0% 602 6.2% 602 5.5% 643 5.3% 1,090 5.6% 1,536 6.8% 1,827 7.5% 974 6.9% 904 6.1% 804 5.6% 720 5.4% 916 4.9% 798 4.5% 654 4.2% 647 4.0% 850 4.7% 1,064 5.8% 1,064 6.0% 704 5.5% 958 5.1% 1,122 4.6% 1,266 4.6% 1,052 5.8% 1,107 9.3% 1,131 9.6% 1,043 8.9% 1,062 8.1% 1,031 7.4% 991 6.2% 979 Lower Educatoin age(16(Labor 24,Labor GDP per force) force) CPI capita 68,375 23,619 107.6 18269.4 68,754 23,367 109.6 19115.0 68,635 22,965 113.6 20100.9 51,800 22,536 118.3 21483.2 54,488 22,134 124.0 22922.5 52,690 21,214 130.7 23954.4 54,693 20,628 136.2 24405.2 51,184 20,454 140.3 25493.0 50,181 20,384 144.5 26464.8 47,191 21,612 148.2 27776.6 46,762 21,453 152.4 28782.2 47,320 21,183 156.9 30068.2 48,516 21,399 160.5 31572.7 48,658 21,890 163.0 32949.2 47,943 22,299 166.6 34620.9 47,446 22,679 172.2 36449.9 47,410 22,690 177.1 37273.6 50,363 22,366 179.9 38166.0 50,573 22,098 184.0 39677.2 50,304 22,268 188.9 41921.8 50,876 22,290 195.3 44307.9 51,112 22,394 201.6 46437.1 50,946 22,217 207.3 48061.5 50,428 22,032 215.3 48401.4 50,332 21,361 214.5 47001.6 50,115 20,935 218.0 48374.1 48,943 20,997 224.9 49781.4 48,099 21,284 229.6 51456.7 47,364 21,381 233.0 52980.0 46,861 21,295 236.7 54629.5 Source: census.gov Avenger-CBM600-Page13 Appendix 2 Regression output SUMMARY OUTPUT Regression Statistics Multiple R 0.8636511 R Square 0.7458932 Adjusted R Square0.6929543 Standard Error 0.0081746 Observations 30 ANOVA df Regression Residual Total SS MS F Significance F 5 0.004707605 0.000942 14.08969436 1.7605E-06 24 0.001603761 6.68E-05 29 0.006311367 Coefficients Standard Error Intercept -0.05225 0.115497092 Immigration(thousand) -3.13E-06 6.91981E-06 Lower Educatoin(Labor 2.451E-06 force) 3.62006E-07 age(16-24,Labor force) -7.01E-06 3.84282E-06 CPI 0.0023268 0.000707888 GDP per capita -7.16E-06 2.41688E-06 t Stat -0.45239 -0.45234 6.771108 -1.8236 3.286923 -2.96423 P-value 0.655051981 0.655088538 5.28507E-07 0.080692246 0.003109517 0.006755082 Lower 95% Upper 95%Lower 95.0% -0.2906238 0.186125 -0.29062 -1.741E-05 1.12E-05 -1.7E-05 1.704E-06 3.2E-06 1.7E-06 -1.494E-05 9.23E-07 -1.5E-05 0.00086577 0.003788 0.000866 -1.215E-05 -2.2E-06 -1.2E-05 Upper 95.0% 0.186124758 1.11517E-05 3.19833E-06 9.23442E-07 0.003787785 -2.176E-06 Avenger-CBM600-Page14 Appendix 3 U.S. Monthly Unemployment Rate, Jan. 2005-Oct. 2015 (in Percentage) Source: U.S. Dept. of Labor, Bureau of Labor Statistics, http://data.bls.gov/cgi-bin/surveymost SUMMARY OUTPUT Regression Statistics Multiple R 0.8636511 R Square 0.7458932 Adjusted R Squar 0.6929543 Standard Error 0.0081746 Observations 30 Coefficients P-value Intercept -0.0522495 0.655052 Immigration(thousand -3.13E-06 0.6550885 Lower Educatoin(Labo 2.451E-06 5.285E-07 age(16-24,Labor force -7.008E-06 0.0806922 СРІ 0.0023268 0.0031095 GDP per capita -7.164E-06 0.0067551
Purchase answer to see full attachment
User generated content is uploaded by users for the purposes of learning and should be used following Studypool's honor code & terms of service.

Explanation & Answer

attached is my work

Considering the data from 1985 to 2014 which presents the relationship between median
wage (in USD) and other independent variables including GDP per capita, annual population
growth, unemployment rate, female/male wage, race and whether people have a bachelor’s degree
or higher. The multiple regression model is then demonstrated as:
y = β0 + β1 x1 + β2x2 + β3x3 + β4x4 + β5x5 + β6x6
where
y = Median Wage
x1 = GDP Per Capita
x2 = Population growth
x3 = Unemployment Rate
x4 = Female/male wage
x5 = Africa America/ White Wage
x6 = Women/men bachelor’s degree or higher
Based on the provided information, a multiple regression analysis that relates the median
wage to all of the remaining variables can be conducted in Excel, and the output is tabulated as
follow:
SUMMARY OUTPUT

Regression Statistics
Multiple R

0.996796

R Square

0.993603

Adjusted R Square

0.991203

Standard Error

709.3355

Observations

23

ANOVA
Significance
df
Regression

SS

MS

F

F

6 1.25E+09 2.08E+08 414.1656

Residual

16

8050510

Total

22 1.26E+09

1.25E-16

503156.9

Standard
Coefficients

Error

t Stat

P-value

Lower 95%

Upper 95%

Intercept

-47156.9

26852.75

-1.75613 0.098187

-104082

9768.43

GDP Per Capita

1.052102

0.079547

13.2262 4.96E-10

0.88347

1.220733

(annual %)

-235.241

2228.822

-0.10554 0.917255

-4960.13

4489.651

Unemployment Rate

-36629.5

12133.03

-3.01899

0.00815

-62350.3

-10908.6

Female/male wage

-62369.9

23024.86

-2.70881

0.01549

-111180

-13559.4

69495.35

22739.25

3.056184 0.007541

21290.29

117700.4

53152.31

26620.16

1.996694 0.063163

-3279.9

109584.5

Population growth

Africa America/ White
Wage
women/men bachelor’s
degree or high

From the above output, we can summarize the multiple-linear equation that connects the
dependent variable median wage (in USD) to all of the independent variables as:

Median Wage = -47156.9 + 1.052* GDP Per Capita - 235.241*Population growth 36629.5*Unemployment Rate - 62369.9* Female/male wage + 69495.35*Race +
53152.31*Educational Degree
Suppose that the significance level is α = 0.05, from the table it follows that the only Pvalues for two variables population growth (annual %) and women/men bachelor’s degree or higher
are 0.917255 and 0.063163, respectively, both of which are greater than α = 0.05. Thus, these two
variables are not statistically significant at 5% significance level, and other variables such as GDP
Per Capita, Unemployment Rate, Female/male wage, and Race are statistically significant in this
regression model since their corresponding P-values are all less than α= 0.05.
In conclusion, since the two variables population growth (annual %) and women/men
bachelor’s degree or higher are not statistically significant, they can be removed from our multiple
regression models in order to form a new one that demonstrates the provided data in a better way,
provided that 5% significance level is used.


Considering the data from 1985 to 2014 which presents the relationship between median
wage (in USD) and other independent variables including GDP per capita, annual population
growth, unemployment rate, female/male wage, race and whether people have a bachelor’s degree
or higher. The multiple regression model is then demonstrated as:
y = β0 + β1 x1 + β2x2 + β3x3 + β4x4 + β5x5 + β6x6
where
y = Median Wage
x1 = GDP Per Capita
x2 = Population growth
x3 = Unemployment Rate
x4 = Female/male wage
x5 = Africa America/ White Wage
x6 = Women/men bachelor’s degree or higher
Based on the provided information, a multiple regression analysis that relates the median
wage to all of the remaining variables can be conducted in Excel, and the output is tabulated as
follow:
SUMMARY OUTPUT

Regression Statistics
Multiple R

0.996796

R Square

0.993603

Adjusted R Square

0.991203

Standard Error

709.3355

Observations

23

ANOVA
Significance
df
Regression

SS

MS

F

F

6 1.25E+09 2.08E+08 414.1656

Residual

16

8050510

Total

22 1.26E+09

1.25E-16

503156.9

Standard
Coefficients

Error

t Stat

P-value

Lower 95%

Upper 95%

Intercept

-47156.9

26852.75

-1.75613 0.098187

-104082

9768.43

GDP Per Capita

1.052102

0.079547

13.2262 4.96E-10

0.88347

1.220733

(annual %)

-235.241

2228.822

-0.10554 0.917255

-4960.13

4489.651

Unemployment Rate

-36629.5

12133.03

-3.01899

0.00815

-62350.3

-10908.6

Female/male wage

-62369.9

23024.86

-2.70881

0.01549

-111180

-13559.4

69495.35

22739.25

3.056184 0.007541

21290.29

117700.4

53152.31

26620.16

1.996694 0.063163

-3279.9

109584.5

Population growth

Africa America/ White
Wage
women/men bachelor’s
degree or high

From the above output, we can summarize the multiple-linear equation that connects the
dependent variable median wage (in USD) to all of the independent variables as:

Median Wage = -47156.9 + 1.052* GDP Per Capita - 235.241*Population growth 36629.5*Unemployment Rate - 62369.9* Female/male wage + 69495.35*Race +
53152.31*Educational Degree
Suppose that the significance level is α = 0.05, from the table it follows that the only Pvalues for two variables population growth (annual %) and women/men bachelor’s degree or higher
are 0.917255 and 0.063163, respectively, both of which are greater than α = 0.05. Thus, these two
variables are not statistically significant at 5% significance level, and other variables such as GDP
Per Capita, Unemployment Rate, Female/male wage, and Race are statistically significant in this
regression model since their corresponding P-values are all less than α= 0.05.
In conclusion, since the two variables population growth (annual %) and women/men
bachelor’s degree or higher are not statistically significant, they can be removed from our multiple
regression models in order to form a new one that demonstrates the provided data in a better way,
provided that 5% significance level is used.


Group Project

Globalization and the US:
Immigration and Unemployment in the US

Avenger-CBM600-Page1

Introdution
Key Word: Unemployment Rate, Immigration, Multiple Linear, and Regression Model

The primary purpose of this report is to determine the relationship of immigration and
unemployment in the United States. First of all, we establish the hypothesis that immigration has
a strong impact on the unemployment in the United States. Besides focusing on the immigration,
we are also going to show the other elements that affect unemployment to reveal a completed
concept of unemployment. With the aim of providing a professional report, all the analyses and
conclusions we will make in this report are all based on accurate statistics from government
reports and websites. The three components of the main body of the report are shown as follows:


Introducing the hypothesis and methodology we will use.



Introducing the variables that effect unemployment



The trend of immigration and unemployment in the latest thirty years in the U.S



Using multiple—linear regression model to analyze how the variables affect unemployment,
and determine which the most significant variable is.

We are about to conclude the relationship between the immigration and unemployment and
determine that immigration has a positive or negative impact on unemployment. Last but not
least, we will present some recommendations according to the conclusion. If immigration brin...


Anonymous
This is great! Exactly what I wanted.

Studypool
4.7
Trustpilot
4.5
Sitejabber
4.4

Related Tags