stories vs statistics

Some of my research has related to the impact of losing a parent on a child’s education in various African contexts. In this work, I have been impressed by the disparity between the dire stories reported in the media and the more hopeful patterns revealed in my statistical analysis.My training is in statistical analysis, but I have been thinking about the value of stories recently. In a recent (excellent) edition of This American Life, I heard the tragic story of a young woman whose mother illegally brought her to the United States as an infant. Now this daughter is finishing college but cannot get a job because of a choice completely out of her hands. The story is sad and yet, without some relevant statistics (How many people are affected by this? to start).

That’s not to say that statistics are always convincing: often they are misleading, either by design or through ignorant misuse. Still, when handled right, they can elucidate the broad patterns in a population. Alternatively, statistics rarely reveal intimate dynamics. (This is not because they couldn’t in principle but because the right data is rarely gathered.) There, a story can illuminate.

Dani Rodrik enunciates a nice (if not earth-shattering) balance in his new book One Economics, Many Recipes:

I believe in the need for both cross-country regressions and detailed country studies. Any cross-country regression giving results that are not validated by case studies needs to be regarded with suspicion. But any policy conclusion that derives from a case study and flies in the face of cross-national evidence needs to be similarly scrutinized. Ultimately, we need both kinds of evidence to guide our views of how the world works. (p4)

Leave a Reply

Fill in your details below or click an icon to log in: Logo

You are commenting using your account. Log Out /  Change )

Facebook photo

You are commenting using your Facebook account. Log Out /  Change )

Connecting to %s