Fun With Datasets

Via Tyler Cowen, an example of the kind of striking new research that we can expect more of as information technology and growing computer literacy make it ever easier for researchers to explore correlations.

Tatu Westling of the University of Helsinki reports:

This paper explores the link between economic development and penile length between 1960 and 1985. It estimates an augmented Solow model utilizing the Mankiw-Romer-Weil 121 country dataset. The size of male organ is found to have an inverse U-shaped relationship with the level of GDP in 1985. It can alone explain over 15% of the variation in

GDP. The GDP maximizing size is around 13.5 centimetres, and a collapse in economic development is identified as the size of male organ exceeds 16 centimetres. Economic growth between 1960 and 1985 is negatively associated with the size of male organ, and it alone explains 20% of the variation in GDP growth. With due reservations it is also found to be more important determinant of GDP growth than country's political regime type. Controlling for male organ slows convergence and mitigates the negative effect of population growth on economic development slightly. Although all evidence is suggestive at this stage, the 'male organ hypothesis' put forward here is robust to exhaustive set of controls and rests on surprisingly strong correlations.

Moral of the story: Empirical work is important, but you always want to see a strong theoretical basis for conclusions.