|
|
2-1-1 Mediation with Dichot Outcome a... |
|
Message/Author |
|
Kevin Wolff posted on Wednesday, January 07, 2015 - 4:05 pm
|
|
|
Hi There, I am attempting to run a two-level 2-1-1 mediation model where the mediator(extfam) and outcome (tcn_vop) are dichotomous, the level-2 IV (cimmicon) is continuous. I have been using page 25 the below presentation as a guide: http://www.afhayes.com/public/aps2013.pdf Variable: Names are cnty tcn_vop extfam cimmcon ; USEVARIABLES ARE cnty tcn_vop extfam cimmcon; cluster is cnty; between is cimmcon; categorical is tcn_vop extfam; ANALYSIS: TYPE= twolevel random; Model: %WITHIN% s_b|tcn_vop on extfam; %BETWEEN% [s_b] (bw); extfam on cimmcon (a); tcn_vop on extfam (bb); tcn_vop on cimmcon (cp); s_b with extfam tcn_vop; MODEL CONSTRAINT: new (direct indirect); indirect= a*(bw+bb); direct= cp; After running the code above, I get the following error. But it seems that I have specified the between and within components as denoted in Hayes' example. Only cimmcon is at level-2 as with the example. Any advice would be greatly appreciated. *** ERROR in MODEL command Observed variable on the right-hand side of a between-level ON statement must be a BETWEEN variable. Problem with: EXTFAM |
|
|
You use the extfam variable as a predictor on both within and between by which I think you mean that you want to consider a latent variable decomposition of extfam into a within and a between component. That decomposition, however, is not available when a random slope is defined for the variable (see UG ex 9.2). You can create a cluster-level counterpart by using the Cluster_Mean option. |
|
Back to top |
|
|