To study the effect of police, consider a natural experiment based on geography, where a patrol boundary of the University of Pennsylvania police department was created that added extra police to city blocks that are adjacent to the university. The assignment of extra police to this area was made without consideration to the population in the adjacent blocks or other covariates of crime. We can capitalize on the discontinuity in police force size at the geographic boundary to estimate the effect of the extra police on crime.

Consider the regression

Crime_i = 0 + W_i + _1d_i + v_i , where Crime is the crime rate of a block, W is a dummy indicator that assumes value 1 for each block (denoted i) inside the patrol zone boundary, d denote the distance to the boundary with a negative value if the block is inside the patrol zone and positive value if the block is outside of the patrol zone. (You don't have to worry about how this distance is measured.)

What represents the effect of Penn police with this regression discontinuity design? (Your answer should be in terms of parameters in the regression equation). How to estimate this parameter?