Felix Rusche @felixrusche.bsky.social · 03/12/2024I then compute coverage areas and match these with DHS survey data. For identification, I exploit topographic features between radio towers and receivers, a standard approach in the literature. 100
Felix Rusche @felixrusche.bsky.social · 03/12/2024In addition, I solve an important issue of the underlying household survey data: To preserve respondents’ privacy, coordinates of survey locations are randomly displaced prior to being made available to researchers. This introduces substantial bias. 100
Felix Rusche @felixrusche.bsky.social · 03/12/2024I build on the displacement algorithm and external data to compute the PDF of original locations, conditional on observing a displaced location. I then compute the probability mass on the coverage area. This allows for clean identification of parameters despite the displacement. 100
