Forum: Would you rather analyze a dataset with a strong, non-collinear batch effect, or a weak, collinear batch effect.
Suppose you generated a dataset that you were really excited about, but had to choose one of the following two options:
1) the data are afflicted by a weak batch effect of some kind, and this batch effect is collinear with an important variable (either the response variable or one of the most important predictors)
OR
2) the data are affected by a strong batch effect, but this batch effect is not significantly correlated with the response variable or any of the most important covariates you plan to include in the model.
Would you choose 1 or 2, and why?
0 answers
No answers yet.
Log in to answer this question.
More posts like this
-
RUVg workflow with DESeq2: covariates in first-pass design, and collinearity between W factors and …
written by gallimaria657 •
-
What is the right choice of normalization and preprocessing before WGCNA using RNAseq data in a coh…
written by sukeshinik5 •
-
Adjusting covariate in regression model
written by Jonathan Yoou •
-
How to assess which cell population is most affected by treatmant in single cell rna seq data?
written by abbas89 •
-
scRNA seq integration
written by friguiahlem8 •
-
How can I do hypothesis test for continuous dependent variable and two categorical independent vari…
written by BioDH •
-
PRS regression and covariates
written by Silvia •
-
Batch effect control in GWAS data.
written by saksis.rihards •
-
Calculate scaling factor for RNAseq data
written by pbigbig
-
removing confounding batch effect with RUVseq
written by grant.hovhannisyan
It depends on what kind of dataset you are talking about.
Is it a gene expression data? If yes, is the batch variable known or you have to estimate it from the data?
its hypothetical - would it make a difference to you if it is expression data or something else ? If so, that would be a great subject for a response!!! :-)