Skip to main content

Table 5 Mean decrease in accuracy for conditional variable importance values and ranking (in parentheses) for the Population Density, Poverty, and Sub-Region variables in each model. Mean Average Error (MAE), Root Mean Squared Error (RMSE), and the Coefficient of Determination (R2) is reported for each model. 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

  

Importance Average (rank)

Accuracy Metrics

 

HC Level

Scenario

Population Density

Poverty

Sub Region

MAE

RMSE

R2

Mtry

HC II

1

1018 (1)

457 (2)

96 (3)

30.96

44.47

0.54

2

2

274 (1)

265 (2)

103 (3)

21.42

30.12

0.41

2

HC III

1

1346 (1)

988 (2)

221 (3)

39.18

53.64

0.54

2

2

183 (1)

174 (2)

50 (3)

17.6

23.22

0.45

2

HC IV

1

5904 (1)

2248 (2)

250 (3)

67.53

88.95

0.5

3

2

876 (1)

455 (2)

180 (3)

30.85

39.3

0.49

3

Hospital

1

13,657 (1)

5253 (2)

3208 (3)

105.77

139.37

0.52

3

2

2729 (1)

1356 (2)

850 (3)

51.43

68.74

0.49

3

RRH

1

68,744 (1)

17,289 (2)

12,533 (3)

158.22

215.48

0.69

3

2

13,658 (1)

4170 (2)

2733 (3)

84.42

111.87

0.63

2

NRH

1

104,105 (2)

37,625 (3)

377,319 (1)

297.31

426.44

0.9

2

2

29,039 (2)

10,445 (3)

95,322 (1)

122.68

170.74

0.93

3