|
Message/Author |
|
|
The data I am working with was collected from 300 persons, each reporting an average of 12 contacts (3 to 49), for each they specified the number of times they contact them face-to-face, by phone, by email and by SMS (300 * 12 * 4). I'm not sure how to model both the interactions (error correlations) between the modes of contact, and account for the panel effect of having multiple observations for each of respondents (as in multilevel or error-component models). Any suggestions? I tried to model it as a twolevel analysis where the between variables measure on the cluster/panel level and the within on the individual level. Is it possible just to include a model where I regress the depended variables (modes) on them selfs? |
|
|
You could set this up in Mplus using TYPE=TWOLEVEL where contacts are nested within individuals. Cluster size would vary from 3 to 49. The outcome is a nominal variable. |
|
|
Thank you for your answer. I will try to integrate the different contact modes as a nominal variable nested within individuals, where the dependent variable consists only of frequency. I also try to model the correlation between the contact modes with endogenous variables, beside the cluster of the 300 persons. Is it possible to include a error correlation for the contact modes beside the clustering of the 300 persons? |
|
|
See Example 9.1. If the dependent variable was nominal instead of continuous, on the between level you would have k-1 random intercepts which you can covary with each other. |
|
Back to top |
|
|