Common dispersion from estimateGLMRobustDisp()
1
0
Entering edit mode
@jane-merlevede-5019
Last seen 4.2 years ago

Dear edgeR users,

In a standard edgeR analysis, when using estimateDisp() on a class 'DGEList' for a specific design  estimateDisp(y,design), there is an estimation of the common dispersion, which we can access simply by y$common.dispersion.

When using estimateGLMRobustDisp() instead of estimateDisp(), there is no estimation of the common.dispersion (unless I am doing something wrong).

Is there a reason why the common dispersion is not computed?

Thank you in advance

 

edgeR dispersion • 1.0k views
ADD COMMENT
1
Entering edit mode
Aaron Lun ★ 28k
@alun
Last seen 14 hours ago
The city by the bay

The authors just didn't feel like putting it in, I guess. estimateGLMCommonDisp supports weights, so there's no reason to avoid calculation of the common dispersion. (It's probably not necessary to calculate it at every robustness iteration, where only the trended dispersion is used.) If you want it, you can just take the output of estimateGLMRobustDisp and feed it to estimateGLMCommonDisp; the weights will automatically be extracted and applied to compute the common dispersion.

ADD COMMENT
0
Entering edit mode

Ok, thank you, I will try.

ADD REPLY

Login before adding your answer.

Traffic: 617 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