|
|
 |
| 2-Level Multilevel Model Error |
 
|
| Message/Author |
|
|
| Chao Yawo posted on Thursday, July 23, 2020 - 7:45 pm
|
|
|
Hello,
I am fitting an HLM model, using DHS survey dataset. It is a two level model with individuals nested in clusters.
My basic model examines the the effect of gender, then marital status on engagement in riskysex (CONDNPSX), while controlling for a level 2 variable (PAIDSCRT).
However, the model is returning the error below:
** ERROR
One or more between-level variables have variation within a cluster for
one or more clusters. Check your data and format statement.
Does it have something to do with the weight variable? I can only supply sample weights for Level 1 variable, and have no weights for Level 2 (cluster-level) variables.
I will be grateful for some insights in resolving this issue.
thanks - cY |
|
|
|
|
| It does not have to do with the weight variable but one or more of your analysis variables. If this doesn't help, send your output to Support along with your license number. |
|
|
| Chao Yawo posted on Saturday, July 25, 2020 - 10:12 am
|
|
|
ok. thanks so much. Given that I have only level 1 weights, do I have to do some scaling to run the MLM model?
thanks, CY |
|
|
|
|
No. The weights are scaled by default
https://www.statmodel.com/download/Scaling3.pdf |
|
|
| Chao Yawo posted on Monday, July 27, 2020 - 7:10 pm
|
|
|
Thanks, Tihomir.
There are no Level 2 weights with my data. Could I still be able to run an HLM/MLM model?
Thanks - cY |
|
|
|
|
| Yes |
|
|
| Back to top |
|
|
