|
|
R3ste/du3ste of GMM(w/p covariate)... |
|
Message/Author |
|
Ahn,Taeyong posted on Thursday, September 14, 2017 - 12:00 am
|
|
|
Dear Mplus team. I did r3step of GMM(w/o covariate) and du3step of GMM(w/o covariate). [r3step] variable: The name is id x1-x19 y1-y4; usevar = y1-y4; Auxiliary = (r3step) x1-x19; Missing = All (-999); Class = c (3); Analysis: type = MIXTURE ; STARTS = 100 10; STITERATIONS = 10; Model: %overall% i s q | y1@0 y2@1 y3@2 y4@3; [du3step] VARIABLE: names are id y1-y4 z1 z2; usevar = y1-y4 ; auxiliary = (du3step) z1 z2 ; missing = all (-999); CLASSES = c(3); Analysis: type = MIXTURE ; STARTS = 100 10; STITERATIONS = 10; Model: %OVERALL% i s q | y1@0 y2@1 y3@2 y4@3; Is it O.K.? |
|
|
Looks fine. You might try BCH instead of du3step; see http://www.statmodel.com/examples/webnotes/webnote21.pdf |
|
Back to top |
|
|