The results reported on slide 4.15 show the standard deviation of education and income. Sigma of 2.52613 means that on average the standard deviation is 2.52613. When we look at 4.15 we can see a beta1 and a beta2. Beta1 represents the y-intercept in which the regression line will hit the y-axis at (0,-0.65207). This y-intercept is crossing close to the (0,0) point but we must look at beta2 to give us more information and see how the line will travel. Beta2 is the slope of the regression line and it shows a slope of 0.36713. The slope of 0.36713 shows that starting at the y-intercept, beta1, the regression line will go up 0.36713 boxes and go one box to the right. Because this slope is small, the line will be flat as it is traveling along the x-axis at a faster rate than the y-axis. In regards to our variables this means that for every increase in one unit of education, there will be an increase of 0.37613 unit of income. The three stars indicated next to the P value shows us that the relationship is significant and the two stars show it’s significance but it is less than a three star.

The results on slide 4.19 show us the standard deviation, while keeping the mu untouched and introducing the explanatory variable to show what the sigma or standard deviation of income will be. We see that we have the average or mu value at 3.51676. Our theta1 value represents the y-intercept or where the regression line will hit the y-axis. The theta1 value is given to us at 1.46101, the regression line begins at (0,1.46101). This also shows us that on average, people with no education at all, their standard deviation income in 1.46101 units. The theta2 value represents our slope value of 0.10908, the rate at which the regression is increasing. In other words, one year income of education increases the standard deviation of income at average at standard deviation of 0.10908. The p values all have three stars which represents a high significance level. Both results show us that there is a significance between education and income.

If we were to introduce a second independent variable of age, we now have to look at not only the relationship between age and income but also age and education levels. I believe that both values of mu and sigma will decrease because we have to consider the affects of age in both of the original variables. If we were to run the regression, age would affect the education level and then that number would have to be the number to use when we are trying to create the relationship with income.