Skip to main content

Table 4 Result from a random intercept model (a measure of variation) for PNC at cluster level by multilevel logistic regression analysis, EDHS 2016

From: Factors associated with postnatal care utilization among postpartum women in Ethiopia: a multi-level analysis of the 2016 Ethiopia demographic and health survey

Measure of variation

Model 0 (Null model) (95% CI)

Model 1 (95% CI)

Model 2 (95% CI)

Model3 (Full model) (95%CI)

Variance

2.37

1.77

1.52

1.50

Explained variation (PCV) (%)

Ref.

25

35

37

ICC (%)

42 (30.00, 53.99)

35 (24.62, 45.37)

32 (22.33, 41.66)

31 (21.39, 40.61)

MOR

3.97 (3.85, 4.09)

3.42 (3.31, 3.2)

3.18 (3.08, 3.27)

3.15 (3.05, 3.24)

Model fitness

Log-likelihood

− 552.68

− 466.41

− 525.29

− 451.52

  1. Model 0 = without independent variables (null model), Model 1 = only individual-level variables, Model 2 = only community-level variables, Model 3 = both individual and community-level variables, PCV Proportional change in variance, ICC Intra-class correlation coefficient and MOR Median odds ratio