Question: RnaSeqSampleSize - unbalanced design
0
gravatar for Adrian Johnson
13 months ago by
Adrian Johnson330 wrote:

Dear group,

I use RnaSeqSampleSize package for calculating power analysis.

Documentation for this package suggests the following usage:

sample_size(power = 0.8, m = 20000, m1 = 200, f = 0.1, k = 1, w = 1,rho = 2, lambda0 = 5, phi0 = 1, showMessage = FALSE,storeProcess = FALSE)

where k = Ratio of sample size between two groups.

In the case of an unbalanced design (e.g., 70 in group A, and 30 in group B), how k should be defined. (k = 70/30 = 2.333)

sample_size(power = 0.8, m =15000, m1 = 400, f = 0.01, k = 1, w =1,rho = 2, lambda0 = 10, phi0 = 0.5)

[1] 50

sample_size(power = 0.8, m =15000, m1 = 400, f = 0.01, k = 2.3, w =1,rho = 2, lambda0 = 10, phi0 = 0.5)

[1] 3

As shown above sample size of 50 and 3 for k = 1 and 2.3 respectively is not correct.

Perhaps, I am not defining k properly. Could anyone help understand this. I appreciate your help.

Thanks!

rnaseqsamplesize • 146 views
ADD COMMENTlink modified 13 months ago • written 13 months ago by Adrian Johnson330
Please log in to add an answer.

Help
Access

Use of this site constitutes acceptance of our User Agreement and Privacy Policy.
Powered by Biostar version 16.09
Traffic: 249 users visited in the last hour