Skip to main content

Table 7 Real data results: parameter estimates with standard errors and p-values from the two-latent classes model with covariates

From: Joint latent class model: Simulation study of model properties and application to amyotrophic lateral sclerosis disease

number of observations

2525

number of patients

497

average number of longitudinal measure

5

number of events

129

censoring rate

0.74

Sub-model

Parameter

Estimate (se)

p-value

Multinomial logistic regression

ξ01

2.22 (0.31)

<0.001

Weibull model

ζ11

0.48 (0.17)

0.004

 

ζ21

1.48 (0.08)

<0.001

 

ζ12

0.68 (0.21)

0.001

 

ζ22

1.64 (0.12)

<0.001

 

𝜗1

-0.05 (0.01)

0.008

 

𝜗2

-0.05 (0.03)

0.079

 

𝜗3

-0.03 (0.01)

<0.001

 

𝜗4

-0.41 (0.12)

<0.001

 

𝜗5

0.04 (0.01)

<0.001

Linear mixed model : fixed effects

\(\hat {\beta }_{01}\)

9.79 (4.02)

0.015

 

β11

-2.32 (0.27)

<0.001

 

β02

7.83 (4.12)

0.057

 

β12

-4.06 (0.39)

<0.001

 

γ1 (SO)

-0.06 (0.02)

<0.001

 

γ2 (BMI)

-0.13 (0.05)

0.009

 

γ3 (MUSC)

0.16 (0.00)

<0.001

 

γ4 (SVC)

1.04 (0.18)

<0.001

 

γ5 (MCV)

0.10 (0.04)

0.007 1

 

γ6 (SO ×tj)

0.02 (0.00)

<0.001

 

γ7 (MUSC ×tj)

0.01 (0.00)

<0.001

 

γ8 (SVC ×tj)

0.06 (0.02)

0.018

Linear mixed model : random effects

\(\sigma ^{2}_{b_{0}}\)

14.10 (0.00)

 
 

\(\sigma ^{2}_{b1}\)

0.18

 
 

\(\sigma ^{2}_{\epsilon,1}\)

1.97

 
  1. Note: the following covariates and their interactions with time (if significant) are presented: SO (Symptom Onset), BMI (Body Mass Index), MUSC (Muscular capacity), SVC (Slow vital capacity), MCV (Mean corposcular volume)