Table 8 Difference in Predictive Accuracy of models for Mean Average Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R2) between Random Forest Model (Ref) and Linear Mixed-Effects Model for each Health Unit Level and Each Response Scenario. Scenario 1 represents the time in minutes walking to the nearest health facility, while scenario 2 represents the time in minutes reduced to health facility using a bicycle instead of walking
From: Exploring country-wide equitable government health care facility access in Uganda
HC Level | Scenario | MAE | RMSE | R2 |
|---|---|---|---|---|
HC II | 1 | −2.75 | −4.29 | 0.09 |
2 | −3.46 | −4.10 | 0.17 | |
HC III | 1 | −4.79 | −5.32 | 0.09 |
2 | −2.05 | −2.99 | 0.15 | |
HC IV | 1 | −8.33 | −8.94 | 0.11 |
2 | −5.79 | −7.38 | 0.21 | |
Hospital | 1 | −28.71 | −33.09 | 0.25 |
2 | −15.38 | −17.44 | 0.28 | |
RRH | 1 | −78.88 | −94.62 | 0.34 |
2 | −35.38 | −43.39 | 0.35 | |
NRH | 1 | − 134.99 | − 130.85 | 0.07 |
2 | −80.1 | −82.73 | 0.08 |