|
Message/Author |
|
Alexis Choi posted on Tuesday, November 07, 2017 - 9:41 pm
|
|
|
Dear Dr. Muthen I'm new to Mplus and have encountered an issue when doing latent moderated SEM. The independent and dependent variables are all continuous and I have created interactions. I also have one categorical control variable (with four categories), which I have coded it as three dummy variables, a b c. When I include these dummy variables in the model, I got the error message saying "One or more variables have a variance of zero. Check your data and format statement. " I've checked the data and it shouldn't have zero variance and I don't have any missing points. Do you mind helping with this? Thanks a lot! Alex |
|
|
Put only the three dummy variables on the USEVARIABLES list. Do a TYPE=BASIC with no MODEL command. Use the SAVEDATA command to save these variables so you can look at them and their sample statistics. This should reveal the problem. |
|
Back to top |
|
|