Session Ready
Exercise

Offering a Higher Credit Card Limit: a Natural Experiment

A previous exercise in Chapter 7 studied an experiment by a company named CreditCo that involved sending mail offers for recipients to increase their credit limit. While thinking about this experiment, you realized that the weather was different for different customers on the day the offers arrived in customers' mailboxes. Specifically, you realized that heavy storms across the country hit half the zipcodes in the treatment group, while the other half of customers experienced sunny weather the day the offer arrived. You realize this variation in the weather may have created a natural experiment where customers in the rainy zones felt gloomy and decided not to take up the offer, while those in the sunny zones felt cheerful and because of their good mood, took up the offer.

Let's test this hypothesis, specifically:

Instructions
100 XP
  • 1) Compute the average difference in take-up rates (opt_in) among those offered (offered) for rained-out customers vs. sunny customers (rainy).
  • 2) Run a t-test to check if balance in pre-offer credit (balance_pre) is balanced among those whose weather was rainy vs. sunny (rainy).
  • 3) Run a t-test to estimate the average treatment effect of rain (rainy) on post-offer credit balances (balance_post), regardless of whether they were offered the balance increase.