This paper analyzes the impact of sample enlargement on the mitigation of collinearity, concluding that it may mitigate the consequences of collinearity related to statistical analysis but not necessarily the numerical instability. This issue is important in teaching social sciences as it relates to one widely accepted solution for addressing multicollinearity. For a better understanding and illustration of the contribution made by this paper, two empirical examples and two simulations are presented and not highly technical developments are used.
