Question regarding p-values in deseq2
1
0
Entering edit mode
langs005 • 0
@langs005-22365
Last seen 4.3 years ago

I am running models using deseq2. I have a question about the raw p-values and covariates. I run two models without and with covariates. There is a substantial shift upwards in the p-values for the model with covariates. The mean p-value after adjustment is above .6. Any comments?

deseqobjgenus3 <- phyloseqtodeseq2(genus4, formula(~ Western )) model3 <- DESeq(deseqobjgenus3, fitType = 'local') out3 <-as.data.frame(results(model3)) out3 names(out3) = c("mean3", "log2fc3", "se3", "stat3", "p3", "adjp3")

deseqobjgenus1 <- phyloseqtodeseq2(genus4, formula(~ v4age1 + white + hwbmi + site +dtcalors + Western )) model1 <- DESeq(deseqobjgenus1, fitType = 'local') out1 <-as.data.frame(results(model1)) out1 names(out1) = c("mean1", "log2fc1", "se1", "stat1", "p1", "adjp1")

deseq2 p-values normalization • 418 views
ADD COMMENT
0
Entering edit mode
@mikelove
Last seen 22 hours ago
United States

P-values can either go up or down after controlling for covariates in a linear model. I would make the model choice on external factors other than the p-value distribution.

ADD COMMENT

Login before adding your answer.

Traffic: 716 users visited in the last hour
Help About
FAQ
Access RSS
API
Stats

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

Powered by the version 2.3.6