Anonymous posted on Tuesday, September 20, 2005 - 7:39 am
Could you help me? To figure out those error & problems. All stop now.
[Questions] 1. I have lots of missing dataset[even outcome & independencs variables]. Ex)To use 26 case in 378
[Message] The standard errors of the model parameter estimates may not be trustworthy for some parameters due to a non-positive definite first-order derivative product matrix..... Note that the number of parameters is greater than the sample size...(like this)
* Could you give me your opinion?
2.[*** ERROR Categorical variable D11 contains less than 2 categories.] -> Fix input [Categorical = D1-D11(*);] -> After then, [*** ERROR One or more variables have a variance of zero.Check your data and format statement.] Continuous Number of Variable Observations Variance
As a minimum for decent estimation, you need to have at least as many observations as parameters. I suggest you modify your model.
It sounds like listwise deletion of the data which is the default in Mplus is resulting in some variables having no variation or you are readng your data incorrectly. If you cannot figure this out, you need to send your input, data, output, and license number to firstname.lastname@example.org.
I ran into a problem with my multilevel SEM. I test a SEM cross-nationally (with ESS data), accordingly country is my cluster variable. I have 27 countries but somehow Mplus gives me the following error message:
"Data set contains unknown or missing values for GROUPING, PATTERN, COHORT, CLUSTER and/or STRATIFICATION variables. Number of cases with unknown or missing Values: 815"
And in the output, Mplus states that there are only 11 cluster variables, which then leads to problems because I have more parameters than cluster variables.
What could be the problem here? In stata the cluster variable looks just fine (metric variable).