oddratio: Calculation of Zeta(zeta)

In Yuande/MBttest: Multiple Beta t-Tests

Calculation of Zeta(ζ)

Description

Zeta (ζ) is used to measure homogeneity intensity of two subdatasets. If ζ >1, these two subdatasets have good homogeneity; otherwise, ζ <1 indicates that two subdatasets have poor homogeneity (big noise).

Usage

oddratio(XX, na, nb)

Arguments

XX	count data of RNA reads generated by next generation sequencing.
na	number of replicate libraries in condition A.
nb	number of replicate libraries in condition B.

Details

Zeta is defined as

ζ=log(1+\frac{\bar{X}σ^2+1}{\bar{X}_Aσ^2_A+\bar{X}_Bσ^2_B+1})

where ζ is different from ψ. If two subdatasets have big a gap and good homogeneity, then ζ value has much larger than 1.

Value

oddrat

list of zeta values

Author(s)

Yuan-De Tan [e-mail]

References

Yuan-De Tan Anita M. Chandler, Arindam Chaudhury, and Joel R. Neilson(2015) A Powerful Statistical Approach for Large-scale Differential Transcription Analysis. Plos One. 2015 DOI: 10.1371/journal.pone.0123658.

See Also

pratio, mbetattest.

Examples

XX<-matrix(NA,2,8)
XX[1,]<-c(112,122, 108,127,302, 314, 322, 328)
XX[2,]<-c(511, 230, 754, 335,771, 842, 1014,798)
#XX
#     [,1] [,2] [,3] [,4] [,5] [,6] [,7] [,8]
#[1,]  112  122  108  127  302  314  322  328
#[2,]  511  230  754  335  771  842 1014  798
oddratio(XX=XX,na=4,nb=4)

#[1] 3.9432676 0.8762017	
	
# see example in mbetattest

Yuande/MBttest documentation built on Aug. 25, 2022, 12:58 a.m.