4.4 Validity of the results
4.4.1 Multicollinearity
Multicollinearity is another factor that might affect our results, because if our variables are
highly correlated, small changes in the data might lead to erratic changes in the coefficient
estimates. The results of the test for multicollinearity are presented in tables 10 and 11, and
since none of the correlations exceed 0.5 we can conclude that multicollinearity does not
cause a problem in our study.