0
$\begingroup$

I am testing mediation in SPSS, and all Baron Kenny steps are satisfied, but I have problem in last step. When I include mediator, F becomes non significant, but beta is significant and effect is smaller after including moderator. Can I interpret this like mediation? Sample size is 126. Dependent variable is disease severity (psoriasis), predictor is Cloninger`s temperament dimension (reward dependence), and mediator is avoidant coping with stress.

output

$\endgroup$
  • 2
    $\begingroup$ Welcome to CrossValidated. It would help those with expertise in this area if you would provide more detail regarding your analysis. If possible, consider posting the relevant output and providing information regarding the model, sample size, and the covariates and outcome of interest. $\endgroup$ – lmo Sep 9 '16 at 14:22
  • $\begingroup$ I believe the @Lily is referencing: web.pdx.edu/~newsomj/da2/ho_mediation.pdf $\endgroup$ – Jon Sep 9 '16 at 16:51
  • $\begingroup$ @Lily, were you able to satisfy the 1-3 steps listed out in the link I referenced? "Assuming there are significant relationships from Steps 1 through 3, one proceeds to Step 4. In the Step 4 model, some form of mediation is supported if the effect of M (path b) remains significant after controlling for X. If X is no longer significant when M is controlled, the finding supports full mediation. If X is still significant (i.e., both X and M both significantly predict Y), the finding supports partial mediation." $\endgroup$ – Jon Sep 9 '16 at 17:09
  • $\begingroup$ Also, have you considered another model? Your R-squared is super low, meaning your model doesn't have an impact effect in explaining the variance of your dependent variable. A significant F-stat is meaningless if your R-squared is near zero. $\endgroup$ – Jon Sep 9 '16 at 17:12
  • $\begingroup$ yes, steps 1-3 are satisfied. Does that mean that F can be non significant, and I can interpret this like mediation? I am a bit confused because my mentor tells me that F should be significant, and to me it seemed that does not have. $\endgroup$ – Lily Sep 9 '16 at 17:41
1
$\begingroup$

I am not an SPSS expert, but from what I am reading from your output you have two models, Model 1 (top) and Model 2 (bottom). Model 2 has an added predictor with a lower F statistic (5.765 --> 2.651). Additionally Model 2 has an R square of 0.067 which is very low. Indicating the model does not have a good impact.

Also, note that for Model 2, your t-statistics are 2.004 (p-val: 0.47) and 1.628 (p-val: 0.106). Both parameters are not significant at the 0.95 confidence level, hence you cannot report

From the reference I've read (http://web.pdx.edu/~newsomj/da2/ho_mediation.pdf)

If X is no longer significant when M is controlled, the finding supports full mediation. If X is still significant (i.e., both X and M both significantly predict Y), the finding supports partial mediation.

Your mediation factor (the added predictor) is not significant in Model 2. That said, I would not conclude there is a significant mediation factor. In order for you to conclude mediation, both factors have to be significant. Hence, you have two choices.

  1. Rule out the effect of mediation

  2. Lower your confidence level to 0.90, and then you can conclude mediation.

I'd be very cautious with option 2, as your are now modeling your analysis around trying to obtain significant results, vs trying to be as truthful to the data (and null hypothesis) as possible.

If I've misinterpreted something in the output, let me know and I'll adjust my answer.

Thanks

| cite | improve this answer | |
$\endgroup$
  • 1
    $\begingroup$ Thank you for the explanation :) Obviously I will have to interpret this as non significant results.. Option 1 is my other hypothesis :) Although in this case is a similar situation, F is not significant, and the beta is significant :D $\endgroup$ – Lily Sep 9 '16 at 18:24

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service, privacy policy and cookie policy

Not the answer you're looking for? Browse other questions tagged or ask your own question.