There are many variables which affect individual earnings potential. One of the most studied is the returns to education. Is there a strong positive correlation between education and higher income? Does an additional year of education raise earnings and if so by how much? These questions are of considerable importance, not simply as an academic exercise, but rather, to the any individual attempting to choose the most rewarding career while navigating the myriad of opportunities competing for the individuals limited time and resources. The purpose of this analysis is to clearly display that there exists far more than a casual relationship between income and educational attainment.

The effects of the returns to educations have been studied extensively across a wide cross section of categories and subjects including, career paths, age groups and geographic locations to name but a few. Two such studies, recently reviewed, focused on the geographic region of the United Kingdom. One study, by Kevin Denny & Vincent O’Sullivan in the journal Applied Economic Letters(2), looked at whether returns to education can compensate for low ability while the other, by Mary Silles in the Journal of Applied Economics(4), looked more generally at the returns to education for the UK. Both studies utilized time series data from a specific geographic region and regression analysis while attempting to provide evidence in support of their argument. The Silles article, utilizing data from the General Household Survey (GHS) of approximately 13,000 households in England, Scotland and Wales between 1985 and 2003 for men and women and regression analysis techniques finds that the returns to education are strong across all segments however returns to education have shown a slight decline for women and younger workers have come to experience unequal returns to education. The Denny & O’Sullivan study using data, from the British National Child Development Survey and regression analysis, showcases education as a substitute for ability. The authors attempt to hold abilities constant while testing various models of returns to education. The authors find that education can indeed be a substitute for ability but only for those with low ability; therefore the returns to education are high for those with low ability and low for those with high ability. Both articles utilize data from a specific geographic region, the UK, both articles find that the returns to education are clearly positive, even if as in the case of the Denny & O’Sullivan the returns were not as significant for those with high natural ability. Similarly to the two articles mentioned in this paper will use macro data from a defined geographic area, individual U.S. states. However, unlike the Denny & O’Sullivan article I will not be taking ability or any other variable beyond education into consideration.

The question is how does years of education affect income and why are the two correlated? The answer is quite simple it turns out and is based on the standard economic theories of wage differentials and supply and demand. Education contributes to raising overall employee productivity. Improved productivity increases employer profits and thus increases demand for educated labor. As employers compete for the most productive labor, through the mechanisms of the market, they drive up the wages earned by those who have received an education. It is through this process that we can clearly see that there is a strong positive relationship between education and higher income. The purpose of this paper is to showcase, through empirical analysis of data, that there is a strong positive relationship between years of education and higher income.

When taking years of education into consideration holding income as the dependent variable it will be clear that the returns to education are statistically significant. My independent variable includes years of education with my dependent variable being income. Using empirical data analysis tools such as regression analysis models incorporating earning and education data across a wide cross section of society, over time; I will clearly show that there is more than a casual relationship between income and education. Undoubtedly there are numerous other factors such as ability, IQ and motivation which can and certainly do account for variation in the income. For this study I will focus exclusively on years of education and income utilizing a statistical error term to account for all unaccounted for variables. My mathematical model is:

The data used to test my hypothesis was compiled from the US Census’s Current Population Survey (1), broken out by state, which included information on statewide educational attainment levels, and the Bureau of Economic Analysis(BEA)(3) data from the Statewide GDP report, which includes a breakdown of the median household income. The Statewide GDP report provided my independent variable, Income, while the US Census’s Current Population Survey provided my dependent variable, Education. Income is measured by the median household income information provided by the BEA Statewide GDP survey. Education is measured by the percentage of the population with a BA degree from the Census’s Current Population Survey. Utilizing the simple regression model laid out above the data provided by these two organizations allows me to test at the macro level my hypothesis. Utilizing both the BEA and Census data I have provided a table below with descriptive statistics. The table below shows the national average for both median household income and percentage of the population with a BA.

Table 1: Descriptive Statistics for the Sample Size (N) of 51

The table shows that the median household income nationally is $50,248 per year while the percentage of the population with a BA is 27.14%. The table also shows the standard deviation, which tells us how tightly median household income and percent with BA are clustered around the mean. The minimum and the maximum are exactly what they sound to be, the minimum median household income and percentage of the population with BA found across all states and the maximum found for both data sets across all states.

This paper’s hypothesis, when taking years of education into consideration holding income as the dependent variable the returns to education are statistically significant. The data from the below table will show that the higher the percentage of the population with a bachelors degree (BA) the higher the statewide median household income. To be precise the data should show that a per unit increase in the percentage of the population with a BA will lead to an increase in the median household income.

Table 2: Empirical Results for the Test of the Returns to Education Theory

Dependent Variable: Median Household Income

The results of my regression analysis can be found in the table above titled OLS Simple Regression Analysis of Median HH Income as Dependent Variable. By looking at the table we can see that indeed a 1% increase in the percentage of the population with a BA degree does lead to an increase in the median household income of $1,057.72. This is shown under the heading B and percentage w/BA (ind) on the above table. The R-Squared statistic shows us how much, as a percentage, of the increase in median household income can be explained by the increase in the percentage of the population with a BA. In this case you can see that slightly over 50% of the increase in median household income can be explained by an increase in the percentage of the population with a BA. The remaining 50% would be explained by all other unobserved factors such as ability, competition for employees and favorable employer tax policies. In my mathematical regression model, laid out above, this is shown by the symbol ɛ

**or epsilon.**Based upon this papers stated hypothesis it is clear that there is a statistically significant relationship between education and income. This is clearly shown to be the case at the macro level where a state’s median household income is positively affected by the percentage of the population with a BA degree. In fact, this paper can state with 99% confidence that there is a statistically significant relationship between median household income and percentage of the population with a BA degree. This paper can do so because at the 99% confidence level, the t-statistic critical value would be 2.48, since the t-statistic is, in fact shown in table 2 to be, 5.29 for the median household income and 7.20 for percentage of the population with a BA, both of which exceed the critical value of 2.48, this paper can be highly confident that there is a statistically significant relationship between median household income and percentage of the population with a BA degree.

The questions originally asked by this report was, is there a strong positive correlation between education and higher income and does an additional year of education raise earnings and if so by how much? It is clear from the empirical data analysis done in this report that education does contribute at least 50% to an increase in the median household income. The amount of the increase, at the state level, is shown to be $1,057.72 for each additional percentage of the population which obtains a BA degree. This report has shown that this result can be given with 99% confidence. Although this topic has been studied extensively, the results of this study should be viewed no less importantly. The results of this paper’s simple regression model, should allow all reader to clearly see that there are statistically significant returns to education. This paper cannot tell the reader their individual returns to education as this paper looks only at the macro effect across all U.S. states, that said, it should be clear to the reader that regardless of their individual scenario the vast majority of readers would benefit from a BA degree. The Denny & O’Sullivan study stated that the returns to education are lower for those of high ability; this may be accounted for in this paper’s model whereas education is shown to only contribute slightly over 50% to the increase in median household income. Even taking the fact that other factors contribute almost 50% of the increase in median household income, the reader can see that there is still a statistically significant return to education. Education accounts for slightly more than 50% where as all other unknown variables combined account for less than 50%. This shows that education clearly represents the very best opportunity to increase household income from all other variables. From the analysis done in this paper the average reader can very feel confident that an investment in education will pay off in a higher household income.

**Works Cited**

1) Census, US. "Current Population Survey."

*U.S. Census*1 (2007): 1.2) Denny, Kevin , and Vincent O'Sullivan. "Can education compensate for low ability."

*Applied Economic Letters*14 (2007): 675-660.3) Economic Analysis, Bureau of . "Statewide GDP."

*Bureau of Economic Analysis*1 (2007): 1.4) Silles, Mary. "The Returns To Education For The United Kingdom."

*Journal of Applied Economics*1 (2007): 391-413.
## No comments:

## Post a Comment