Classifying Patients with Chronic Pelvic Pain into Levels of Biopsychosocial Dysfunction Using Latent Class Modeling of Patient Reported Outcome Measures

Table 2

Average latent class probabilities for most likely latent class membership (row) by latent class (column) according to a four-class model. For each column the probability is shown for the LCA method to assign patients into the different classes. A good model would have a high probability of properly assigning each class (1 s into Class 1, 2 s into Class 2, etc.) and a low probability of misclassification (1 s into Class 2, 3, or 4, etc.).

Class	1	2	3	4
1	0.896	0.000	0.104	0.000
2	0.000	0.879	0.110	0.011
3	0.072	0.047	0.881	0.000
4	0.000	0.078	0.001	0.921