What In-Store Analytics Sees That Sales Data Cannot

In 1943, Abraham Wald was handed a question about bombers returning from missions over Europe. The aircraft were coming home with bullet holes scattered across their wings, fuselage, and tail, and the instinctive conclusion was straightforward: reinforce the areas taking the most damage. Wald, working with the Statistical Research Group at Columbia University , saw that the problem lay not in the analysis but in the sample.