Skip to main content

Table 2 Comparison of LCA Models with Different Latent Classes Based on Model Selection Statistics among Iranian University Students, 2019

From: Health-risk behaviors among Iranian university students, 2019: a web-based survey

Number of latent Classes

Number of parameters estimated

G2

df

AIC

BIC

Maximum log-likelihood

1

5

1806.28

53

1826.28

1888.28

− 6824.14

2

11

124.29

41

168.29

304.71

− 5983.15

3

17

48.75

29

116.75

327.58

− 5945.38

4

23

25.70

17

117.70

402.94

− 5933.86

5

29

13.34

5

129.34

488.98

− 5927.67

6

35

6.81

146.81

580.87

− 5924.41

7

41

6.86

170.86

679.32

−5924.43

  1. Note. LCA latent class analysis, AIC Akaike Information Criterion, BIC Bayesian Information Criterion