Syndicate content

matched difference-in-differences

How big data helped us estimate the impact of an intervention with 0.8% take-up

Claudia Ruiz's picture

When asked if he would like to have dinner at a highly-regarded restaurant, Yogi Berra famously replied “Nobody goes there anymore. It’s too crowded”. This contradictory situation of very low take-up combined with large overall use is common with some financial products – for example, the response rate to direct mail credit card solicitations had fallen to 0.6 percent by 2012, yet lots of people have credit cards.

It is also a situation we recently found ourselves in when working on a financial education experiment in Mexico with the bank BBVA Bancomer. They worked with over 100,000 of their credit card clients, inviting the treatment group to attend their financial education program Adelante con tu futuro (Go ahead with your future). Over 1.2 million participants have taken this program between 2008 and 2016, yet only 0.8 percent of the clients in the treatment group attended the workshop. A second experiment which tested personalized financial coaching also had low take-up, with 6.8 percent of the treatment group actually receiving coaching.

In a new working paper (joint with Gabriel Lara Ibarra), we discuss how the richness of financial data on clients allows us to combine experimental and non-experimental methods to still estimate the impact of this program for those clients who do take up the program.