Yolande Tra posted on Tuesday, February 16, 2010 - 7:06 pm
The output of a mediation analysis is as follow STANDARDIZED MODEL RESULTS STDYX Standardization Two-Tailed Estimate S.E. Est./S.E. P-Value Y ON GROUP 0.047 0.239 0.195 0.845 X1 -0.315 0.152 -2.063 0.039 where GROUP is dichotomous (control and treatment), X1 and Y are continuous. How would you interpret the estimate -0.315 for control group?
I'm not sure what your question is. If y is continuous, -.315 is a standardized linear regression coefficient.
Yolande Tra posted on Friday, February 19, 2010 - 6:58 am
I am sorry for the unclear question. Group has two values 1: treatment, 0: control. Group is not significant. I believe -0.315 is the change in Y (in standard deviation units) when X1 increases by 1 std deviation unit, controlling for group. Does this mean it is the effect of X1 on Y for both treatment and Control?