Time serious analysis Wald test in results()
Entering edit mode
Jason • 0
Last seen 1 day ago

Hi, In the time course analysis in this vignette (http://master.bioconductor.org/packages/release/workflows/vignettes/rnaseqGene/inst/doc/rnaseqGene.html#time-course-experiments). It said using the following code, "the interaction terms are the difference between the two groups at a given time after accounting for the difference at time 0"

ddsTC <- DESeq(ddsTC, test="LRT", reduced = ~ strain + minute)
resTC <- results(ddsTC)

And then in the following analysis in that vignette, it said "Wald tests for the log2 fold changes at individual time points can be investigated using the test argument to results", and use the following code (I change minute30 to minute180)

resTC <- results(ddsTC, name="strainmut.minute180", test="Wald")

My question is : does using Wald test in the results function here also accounts for the difference at time 0? I compare the two resTC results. The fold changes are exactly the same, but the p value is different. I understand different P value is because "reslts (ddsTC)" compare the full and reduced model, while defining test="Wald" only compare mutant to wt at minute180. But why are fold changes the same?

Please correct me if I am wrong.

DESeq2 TimeSeriesExperiment • 92 views
Entering edit mode
Last seen 3 hours ago
United States

Yes those interaction terms account for differences at time 0, and so do Wald tests of those coefficients.

It sounds however like you are confusing a Wald test of a specific time point with an LRT. See the vignette section on LRT.


Login before adding your answer.

Traffic: 260 users visited in the last hour
Help About
Access RSS

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

Powered by the version 2.3.6