Economists will often caution that correlation does not necessarily imply causation, or that causation may not run the way you expect. So, for example, the negative correlation between educational attainment and crime, that more educated people are less likely to be criminals, might not have to do with the improving effects of education. It might be because an unobserved factor, e.g. a lack of conscientiousness, makes a person more likely to be a criminal and less likely to pursue education. Or that being a criminal denies you educational opportunities. Resolving the existence and direction of causality between education and crime can be important for public policy, because it could justify additional resources devoted to education, with a view to reducing crime.
Earlier this decade, LSE Professor Stephen Machin and his colleagues used innovative statistical techniques, based on the quasi-experiments generated by changes in the compulsory school leaving age in Britain, to prove that education does have a negative impact on crime (see this LSE working paper, later published in the prestigious Economic Journal).
LSE’s Professor Machin is one of the world’s leading experts in using innovative techniques to evaluate the impact of public policy measures. The Economic Society of Australia (Qld), of which I am the Secretary, is delighted to have arranged, in conjunction with Griffith University, QUT and UQ, a Winter School on public policy evaluation to be led by Professor Machin at O’Reilly’s Rainforest Retreat on the Gold Coast over 7-9 June:
I would encourage you to book early to avoid disappointment, because this is an incredible opportunity to learn state-of-the-art public policy evaluation techniques from a world leader in the field.
View from accommodation at O’Reilly’s Rainforest Retreat
By thinboyfatter [CC BY 2.0 (http://creativecommons.org/licenses/by/2.0)%5D, via Wikimedia Commons