|
|
Adjusting Standard Error for Pairwise... |
|
Message/Author |
|
|
Dear Drs. Muthen, I was trying to estimate an actor-partner interdependence model (APIM; Kenny et al., 2006) in SEM and have used a pairwise data entry format. Using this approach, the sample size has become double. For instance, if I have 100 couples, the sample size would become 200. Because the unit of analysis should be at the couple level, I would like to adjust the estimates (and standard errors) based on N = 100, instead of 200. Is there a way I can specify that in Mplus? |
|
|
You could use TYPE=COMPLEX or TYPE=TWOLEVEL with couple as the cluster variable. It would show sample size 200 but in estimation independence of observations would be at the couple level. |
|
|
Thank you so much Dr. Muthen! |
|
Back to top |
|
|