Research on this issue has been sharply limited by available data. Some of the data that scholars most fervently covet…are deliberately concealed or misreported by governments. Until recently, most studies have been based on the statistical analysis of large datasets with a single observation for each country and year, datasets that have been mined up to (and perhaps beyond) the point of diminishing returns. There is a promising trend toward subnational research, where the data are often better and identification strategies more convincing. Future progress will depend on our capacity to find new data, including both cross-national and sub-national data, that can cast light on the many unresolved puzzles.
That’s from a recent paper by UCLA’s Michael Ross. Ross was talking about research on the natural-resource curse, but I think his description applies pretty well to quantitative analysis on every topic in comparative politics and international relations I know well. Political and economic development, war within states, war between states, coups—I can’t think of a single major exception. If you can, please say so in a comment.