DID Regression

The predictive model was fitted on the treatment group and the matching control group before and after the project completion. We then applied difference-in-difference regression on the predicted internet speed to test if the average difference is statistically significant. \[ PredictedSpeed_{h,t} = \alpha + \beta treatment_h + \gamma year_t + \delta_{DD}treatment_h * year_t + e_{h,t} \] The results indicate that there is a significant improvement in predicted internet speed in the project area compared with the matching control group after the project completion.

DID Regression Result
DID Regression Result

Program Contacts: Joel Thurston and Cesar Montalvo