Statistics: AIDS in Africa
Here's an excellent Harvard paper by Emily Oster which describes the problem and suggests some well argued explainations.
In 2003, 2.3 million people in Sub-Saharan Africa died of AIDS. In the same year, there were 3.1 million new HIV infections, bringing the total number of HIV infections to 25.4 million [UNAIDS 2004]. Though AIDS is a worldwide problem, Sub-Saharan Africa has been much more heavily affected than elsewhere. The valence rate for pregnant women (the most widely tested group) is 0.15 percent in the United States, and ten to fifteen percent in Sub-Saharan Africa. There is also enormous variation in HIV infection rate within Africa - the prevalence in Madagascar is under one percent but it is over twenty percent in Botswana, Zimbabwe and elsewhere [UNAIDS 2004]. To this point, the reason for the enormous variation remains poorly understood.
Though it is one of the most important and most thouroughly studied problems in the world, it's is a demographer's nightmare because of the complexity, unreliability, and the sheer horror of looking at the data. (Hat tip: Marginal Revolution)