|
|
Missing data: mediation with count ou... |
|
Message/Author |
|
Anne Chin posted on Wednesday, April 12, 2017 - 6:36 pm
|
|
|
I am using a mediation model to examine indirect effects. I have a continuous IV, 4 continuous mediators, 1 categorical mediator & a count outcome variable. My input is as follows: analysis: estimator=ml; integration=montecarlo; bootstrap=5000; model: M1 on x1 (a1); m2 on x1 (a2); m3 on x1 (a3); m4 on x1 (a4); m5 on x1 (a5); y1 on M1 (b1); y1 on m2 (b2); y1 on m3 (b3); y1 on m4 (b4); y1 on m5 (b5); y1 on x1 (c); Model Constraint: new (med1 med2 med3 med4 med5 med_total total); med1 = a1*b1; med2 = a1*b2; med3 = a1*b3; med4 = a1*b4; med5 = a1*b5; med_total = med1+med2+med3+med4+med5; total = c + (a1*b1) + (a2*b2) + (a3*b3) + (a4*b4) + (a5*b5); output: samp standardized tech1 CINTERVAL(BOOTSTRAP); However, I get the following warning: *** WARNING Data set contains cases with missing on x-variables. These cases were not included in the analysis. Number of cases with missing on x-variables: 17 1 WARNING(S) FOUND IN THE INPUT INSTRUCTIONS How do I see the output? Do I need to modify my code? |
|
|
This question is with Mplus Support. Note also that mediation with a count outcome requires different indirect effects than a*b (see our new book). |
|
Back to top |
|
|