Looking at Tables 4, 5, and 6, there are no exact linear relationships between any of the explanatory
variables, with correlations reaching only a high of 0.65 between GDP per capita and bachelor’s degree in
2006. The fourth assumption concerns the zero conditional mean, which indicates that the error u has an
expected value of zero given any values of the independent variables. The fifth assumption,
heteroskedasticity, also concerns the error u, which should have the same variance given any value of the
explanatory variables. There was no way to assure that both assumptions were held, so methods such as
estimating a multivariate model will further reduce the likelihood of biasedness in the model.