Question: Limma - Using removeBatchEffect before differential expression analysis
0
5 weeks ago by
jmoon11940 wrote:

For a dataset I'm working on, we would like to use the limma package for differential expression analysis. We are using limma::removeBatchEffect (doing it for downstream analysis) before using limma for differential expression analysis. Would it be okay to still include the batch covariate in the model to account for degrees of freedom, even though it's been already corrected for?

modified 5 weeks ago by James W. MacDonald49k • written 5 weeks ago by jmoon11940
Answer: Limma - Using removeBatchEffect before differential expression analysis
2
5 weeks ago by
United States
James W. MacDonald49k wrote:

Using removeBatchEffect and then adding in the covariate to the model is what you would need to do in order to account for the lost degrees of freedom that were used to correct for the batch effect. But that's not really how you should do it. Instead you should just put the batch effect in your model rather than doing this two-step approach.

Content
Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.