I have run a multiple imputation model and after it I used the with() and pool() functions to pool all my results using linear regression to get one estimate.
I want to run mediation analysis on this dataset. I used the complete() function to use one of the imputed datasets, but the problem is that the direct estimate I am getting from this dataset is different (in terms of significance) compared to the results of the linear regression model that came from the pool() function. I believe pool() is more accurate.
How do I run mediation analysis while considering the estimates I am getting from all the imputed datasets?
Here is the code for linear regression after multiple imputation:
X
putation and Mediation Analysi
How to run mediation analysis after multiple imputation in R?
Running mediation analysis after multiple imputation in R involves several steps. Here's a general outline of the process:
- Badges
- Science topic
- Similar topics
- Mathematical Sciences
- Statistics
- Statistical Software
- SPSS