Skip to main content

Table 1 Summary results of health models for the unsupervised methods: (K-means clustering, hierarchical clustering, PCA, and EFA)

From: An overview of methods to address distinct research questions on environmental mixtures: an application to persistent organic pollutants and leukocyte telomere length

Variableβ95% CIP-value
K-means clustering   
Cluster 1 (high exposure)0.080.03, 0.130.001
Cluster 2 (medium exposure)0.050.02, 0.090.005
Cluster 3 (low exposure)Reference
Hierarchical clustering   
Cluster 1 (high exposure)0.050.01, 0.100.03
Cluster 2 (medium exposure)0.03-0.00, 0.070.06
Cluster 3 (low exposure)Reference
Principal Component Analysis   
PC1-0.01-0.02, -0.01<0.001
PC20.001-0.01, 0.010.87
PC30.002-0.01, 0.020.76
Exploratory Factor Analysis   
FA1-0.003-0.03, 0.030.86
FA20.030.00, 0.050.02
FA30.030.01, 0.050.01
FA4-0.02-0.04, 0.000.06