For my Masters thesis, I analyze how air pollution affects travel mode decisions in China using a large and detailed hourly household-level data set on hourly household-level travel mode decisions in Beijing; and hourly air pollution, weather, wind speed, and wind direction in and around Beijing. I use machine learning, LASSO regressions, and atmospheric chemistry to select and construct instruments for air pollution to address its endogeneity. My selected instruments for air pollution include wind speeds at high altitude that disperse pollution and wind blowing from upwind industrial areas towards Beijing that may increase pollution. I compare the effects of air pollution on travel mode before and after China launched a nation-wide, real-time air quality monitoring and disclosure program. According to the results of my IV regressions for 2010, prior to the reform, air pollution makes people less likely to walk; and more likely to bicycle, take bus, take car, take subway, and take other modes of transport; and air pollution decreases both the number and share of household members in each household who took at least 1 trip that hour. In contrast, in 2014, after the reform, air pollution makes people more likely to walk and take a taxi; and less likely to bicycle, take bus, take car, take subway, and take other modes of transport; and air pollution increases the number of members in household who took at least 1 trip that hour.