|
|
Poisson Regression with Mediation |
|
Message/Author |
|
|
Drs. Muthen, Please forgive the elementary question, but I am trying to determine the correct syntax for a mediation analysis with a non-normally distributed outcome variable. In particular, I am struggling with significance tests for the indirect effects. The following is my present attempt. Could you help with clarifying the proper syntax for this analysis? Thank you. Title: Mediation with Poisson; Data: File is “c:\file.dat; Variable: Names are DV MED P1 P2 P3 CLUST; MISSING are all (-999); CLUSTER are CLUST; Usevariables are DV MED P1 P2 P3; Count are DV (nb); Analysis: Type is COMPLEX; Model: DV on P1 (a1) P2 (a2) P3 (a3) MED; MED on P1 (a1) P2 (a2) P3 (a3); Model Test: A1 = 0; A2 = 0; A3 = 0; Model indirect: DV IND MED P1 P2 P3; Output: samp stand cinterval; |
|
|
You cannot have several labels on the same line without using semi colons. |
|
Back to top |
|
|