Skip to main content

Table 1 Performance of latent class growth model and growth mixture model

From: Interpretable classifiers for prediction of disability trajectories using a nationwide longitudinal database

 

BIC

   

LGCM

 linear

105,530.680

   

 quadratic

105,345.372

   

 cubic

105,359.053

   

LCGM

BIC

Entropy

VLMR-LRT

Smallest class

 1-class

111,004.715

  

100%

 2-class

105,054.609

0.942

0.0000

16.173%

 3-class

102,817.976

0.892

0.0000

8.093%

 4-class

101,585.221

0.904

0.0018

3.720%

 5-class

100,586.689

0.881

0.0009

4.278%

 6-class

99,933.216

0.862

0.0153

3.068%

GMM

 3-class

102,109.346

0.929

0.0000

7.158%

  1. Abbreviations: BIC Bayesian information criteria, VLMR-LRT VUONG-LO-MENDELL-RUBIN likelihood ratio test, LGCM Latent growth curve model, LCGM Latent class growth model, GMM, growth mixture model
Back to article page

BMC Geriatrics

ISSN: 1471-2318

Contact us