

Syntax for basic growth model with or... 

Message/Author 


Hi, I have data at 3 time points (0, 1 year later, and then 5 years later), and I'm trying to model change in an ordinal (threecategory) outcome, and want to begin by just looking at the trend without any covariates. I'm using the following syntax (beginning from the "categorical" specification): Categorical are y1 y2 y3 ; Analysis: Type = meanstructure; Estimator= ml ; Model: level trend  y1@0 y2@1 y3@5 ; [y1@1 y2 y3] ; y1y3 (1) ; [level trend] ; When I do this I get the following error: *** ERROR in Model command The categorical variables in the growth model do not have the same number of categories. Use the CATEGORICAL option to allow the number of categories to differ for maximum likelihood estimation. Problem with: LEVEL TREND I'm confused because each "bmicat" variable is coded identically, with three categories and no missings. Is there something obviously wrong here? I am brand new to MPlus and would appreciate any feedback! 


It sounds like you are not reading your data correctly. You may have blanks in the data and are reading it with free format which is not allowed. Send your input, data, output, and license number to support@statmodel.com if you cannot figure it out. 


Hi Professors, I have a similar problem. My code is CATEGORICAL are BINGE1 BINGE2 BINGE3 BINGE4 PSUSCID REGION GSWGT4; STRATIFICATION = REGION; CLUSTER = PSUSCID; WEIGHT = GSWGT4; IDVAR= AID; ANALYSIS: TYPE= COMPLEX; ALGORITHM = INTEGRATION; INTEGRATION = Monte; COVERAGE = .0001; CONVERGENCE =.001; STARTS = 50 10; PROCESSOR =8 (STARTS); ESTIMATOR =MLR; MODEL: i s q BINGE1@0 BINGE2@1 BINGE3@2 BINGE4@3; I get the same message described above by Margot except that at the end I get "Problem with:I S Q" The binge variables have 7 ordinal categories but binge4 has only 6 of them. When I delete BINGE4 from the model it runs fine. I do not know what syntax to use so that the model will run with BINGE4. Could you help me out? Thank you. 


See the * setting of the CATEGORICAL option. 

Back to top 

