Working Paper: NBER ID: w23326
Authors: Seungwoo Chin; Matthew E. Kahn; Hyungsik Roger Moon
Abstract: Urban rail transit investments are expensive and irreversible. Since people differ with respect to their demand for trips, their value of time, and the types of real estate they live in, such projects are likely to offer heterogeneous benefits to residents of a city. Using the opening of a major new subway in Seoul, we contrast hedonic estimates based on multivariate hedonic methods with a machine learning approach that allows us to estimate these heterogeneous effects. While a majority of the "treated" apartment types appreciate in value, other types decline in value. We explore potential mechanisms. We also cross-validate our estimates by studying what types of new housing units developers build in the treated areas close to the new train lines.
Keywords: urban rail transit; real estate prices; machine learning; hedonic pricing; conditional average treatment effects
JEL Codes: R21; R4
Edges that are evidenced by causal inference methods are in orange, and the rest are in light blue.
| Cause | Effect |
|---|---|
| Proximity to the subway line (within 1 kilometer) (R53) | Price appreciation for certain apartment types (R31) |
| Proximity to the subway line (within 1 kilometer) (R53) | Price decline for certain apartment types in Gangnam area (R31) |
| Anticipated effects of the subway (R41) | Pre-treatment price changes (L11) |
| Subway introduction (Y20) | Heterogeneous impacts on real estate prices (R31) |
| Reduced travel times to desirable destinations (R41) | Price appreciation (G19) |
| Increased local retail and restaurant activity (R33) | Price appreciation (G19) |