Skip to main content

Table 1 Parameter estimates for one-part model, two-part (TP) model with uncorrelated random effects, TP with correlated random effects, and marginalized two-part (mTP) models assuming gamma distribution for the non-zero component

From: Analysis of longitudinal semicontinuous data using marginalized two-part model

Model component

Covariate

One-part modela,b: parameter estimate, (SE), P-value

TP model uncorrelated random effectsc: Parameter estimate, (SE), P-value

TP model correlated random effectsd: Parameter estimate, (SE), P-value

mTP modele: Parameter estimate, (SE), P-value

Zero part

Intercept

1.4790, (1.0269), 0.1498

0.5006, (0.1246), < 0.0001

− 0.8797, (0.1737), < 0.0001

− 0.1172, (0.0896), 0.1917

Txt group

0.1582, (0.0942), 0.0932

− 0.2506, (0.1496), 0.0944

− 0.6384, (0.2472), 0.0100

− 0.2899, (0.0609), < 0.0001

Smoking

− 0.2739, (0.2573), 0.2870

0.5177, (0.1944), 0.0080

0.5693, (0.2767), 0.0400

0.6705, (0.0864), < 0.0001

Time

0.0630, (0.0176), 0.0003

0.0355, (0.0190), 0.0626

− 0.5005, (0.0725), < 0.0001

− 0.0657, (0.0165), < 0.0001

Continuous Non-zero part

Intercept

2.5112, (0.3580), < 0.0001

− 1.8443, (0.5939), 0.0020

− 1.9699, (0.4325), < 0.0001

HbA1c

0.0597, (0.0507), 0.2387

− 0.0065, (0.0179), 0.7164

0.0970, (0.0244), < 0.0001

0.0755, (0.0214), 0.0005

Age

− 0.0114, (0.0084), 0.1771

− 0.0121, (0.0041), 0.0045

− 0.0018, (0.0057), 0.7476

− 0.0020, (0.0049), 0.6879

Duration

− 0.0336, (0.0165), 0.0425

− 0.0082, (0.0065), 0.2098

0.0035, (0.0092), 0.7007

0.0030, (0.0081), 0.7072

SBP

0.0103, (0.0073), 0.1614

0.0047, (0.0024), 0.0534

0.0267, (0.0043), < 0.0001

0.0243, (0.0029), < 0.0001

Male

0.0662, (0.1111), 0.5515

0.0501, (0.0637), 0.4330

0.0356, (0.0747), 0.6331

0.0099, (0.0782), 0.8985

HDL

0.0052, (0.0116), 0.6537

0.0058, (0.0024), 0.0195

0.0172, (0.0034), < 0.0001

0.0124, (0.0031), < 0.0001

Time

0.0201, (0.0102), 0.0530

0.0127, (0.0149), 0.3957

− 0.0225, (0.0164), 0.1710

Random effects

Zero part variance

1.0528

0.1894

0.4409

Non zero part variance

0.1620

0.2438

0.3357

Covariance

0.2149

0.3847

  1. One-part modela fits the entire sample without distinction between zero and non-zero processes, so only one estimate for the intercept and one for time were generated. In one-part modelb the parameter estimates for txt group and smoking represent the effect of these covariates on the CTGF levels themselves and not on the probability of non-zero values, unlike the TP and mTP models. TP model uncorrelated random effectsc and TP model correlated random effectsd generate estimates for the continuous part using only a portion of the sample pertaining to positive non-zero values. mTP modele provides estimates for the parameters in the continuous part for the entire sample (zero and non-zero values)