Skip to main content

Table 3 Number of non-converged runs (out of 1000) per setting for latent class distributional regression (LCDR)

From: Latent class distributional regression for the estimation of non-linear reference limits from contaminated data sources

c

n = 500

n = 1000

\(\sum\)

\(\alpha _1\)

\(\alpha _1\)

0.6

0.7

0.8

0.6

0.7

0.8

5

79

87

125

24

58

86

459

10

51

63

105

14

26

60

319

15

23

34

96

3

7

30

193

20

4

17

55

0

1

16

93

\(\sum\)

157

201

381

41

92

192

1064