|
|
Uncorrelated Variables in a LCA |
|
Message/Author |
|
|
Hi, I am trying to run a latent class analysis at one time point to examine individual differences in traditional and cyber forms of victimization (all categorical). When conducting a series of LCAs to determine the best fitting model, I am given a warning on only some of the analysis: *** WARNING in MODEL command All variables are uncorrelated with all other variables within class. Check that this is what is intended. I have been reading about this issue and am still unsure if it is an issue and how I can resolve it. Any advice would be greatly appreciated. Brett Here is part of my syntax for one of the models that I got the error: CLASSES = c(5); ANALYSIS: type = mixture; starts = 500 50; stiterations = 50; algorithm = integration; PLOT: Type = plot3; Series = cv1_4(1) cv2_4(2) cv3_4(3) cv4_4(4) rv1_4(5) rv2_4(6) rv3_4(7) rv4_4(8) rv5_4(9) pv1_4(10) pv3_4(11) pv4_4(12) pv5_4(13) verbal_4(14); OUTPUT: Stand tech11 tech14; |
|
|
This message can be ignored with LCA because you want the variables to be uncorrelated. |
|
|
Sounds great, thanks for the quick response Linda! |
|
Back to top |
|
|