Sample-Selection Biases and the “Industrialization Puzzle”

Understanding long-term changes in human well-being is central to understanding the consequences of economic development. An extensive anthropometric literature purports to show that heights in the United States declined between the 1830s and the 1890s, which is when the US economy industrialized and urbanized. Most research argues that declining heights reflects the impact of the industrialization process. This interpretation, however, relies on sources subject to selection bias. Changes in that selection mechanism may account for the declining heights. We show that the evidentiary basis of the puzzle is not as robust as previously believed. Our meta-analysis of more than 150 studies shows that declining-heights finding emerges primarily in selected samples. Finally, we offer a parsimonious diagnostic test for revealing (but not necessarily correcting for) selection bias. The diagnostic applied to four samples that underlay the industrialization puzzle shows compelling evidence of selection