Hello everyone!
I have conducted a multiple imputation in R with 5 imputations and 50 iterations using the function mice() from the corresponding mice package. Now that I have analysed and discussed all my results I have realised that the default settings of the complete () function is to choose the first imputed dataset out of five.
I did not know that I can choose which dataset I want to work with. Is there a special reason why the default setting is to chose the first dataset and how can I argue that I did so?
Thank you very much for your help.
All the best,
Lili
Here is an excellent explanation of how to use multiple imputation in R: https://www.youtube.com/watch?v=izQB-n-euro&ab_channel=EhsanKarim
Thank you all for the answers and the interesting articles/videos. They are really helpful.
However, my problem is that I have already conducted MI using the mice package without actively deciding about the pooling method but going with the default option of chosing the first dataset.
My question would be know how I can justify that I used the first dataset. Stating that this is the default in R is not a very good argument, isn't it? Or can I use the default argument?
All the best,
- Badges
- Science topic
- Similar topics
- Mathematics
- Statistics
- Statistical Software
- R