Abstract
Does the level of sunlight affect the tipping percentage in taxicab rides in New York City? We examined this question using data on 13.82 million cab rides from January to October in 2009 in New York City combined with data on hourly levels of solar radiation. We found a small but statistically significant positive relationship between sunlight and tipping, with an estimated tipping increase of 0.5 to 0.7 percentage points when transitioning from a dark sky to full sunshine. The findings are robust to two-way clustering of standard errors based on hour-of-the-day and day-of-the-year and controlling for day-of-the-year, month-of-the-year, cab driver fixed effects, weather conditions, and ride characteristics. The NYC cab ride context is suitable for testing the association between sunlight and tipping due to the largely random assignment of riders to drivers, direct exposure to sunlight, and low confounding from variation in service experiences.