|
|
Simultaneous growth model-Complex sur... |
|
Message/Author |
|
|
Hi My model has two processes achievement and teacher expectation using NELS dataset I have repeated measures nested within students and students nested within schools and schools nested within strata. I do not have at school level any predictor variables. The only predictor I have is gender (as initial step but I have other predictors). Both processes are continuous Here is how I specify the model but I got error messages (e.g., psi matrix is indefinite) VARIABLE: Names ARE ID SCHID SSTRATID F2PNLWT Gender RACE SES Math1 Math2 Math3 LOC1 LOC2 LOC3; USEVARIABLE = SCHID SSTRATID F2PNLWT Gender Math1 Math2 Math3 LOC1 LOC2 LOC3; MISSING=ALL(-99); CLUSTER = SCHID; STRATIFICATION = SSTRATID; WEIGHT = F2PNLWT; ANALYSIS: TYPE = MISSING H1 COMPLEX TWOLEVEL; Model: %WITHIN% MathIw MathSw|Math1@0 Math2@1 Math3@2; Math1 Math2 Math3; MathIw MathSw ON Gender; LOCIw LOCSw | LOC1@0 LOC2@1 LOC3@2; LOC1 LOC2 LOC3; LOCIw LOCSw ON Gender; %BETWEEN% MathIb MathSb|Math1@0 Math2@1 Math3@2; [Math1@0 Math2@0 Math3@0]; [MathIb-MathSb]; LOCIb LOCSb|LOC1@0 LOC2@1 LOC3@2; [LOC1@0 LOC2@0 LOC3@0]; [LOCIb-LOCSb]; MathSb LOCIb LOCSb MathIb WITH MathSb LOCIb LOCSb MathIb; OUTPUT: SAMPSTAT standardized TECH4; Thanks |
|
|
This message relates to something about how the model fits your data. You would need to send your input, data, output, and license number to support@statmodel.com for an answer. |
|
Back to top |
|
|