NBBttest (version 1.0.1)

smbetattest: Performance of multiple beta t-test on simulated data

Description

This function is to peform beta t-test with \(\rho\) =1 and \(\omega\)=1 on simulated data. The result lists differentially expressed genes or isoforms and their \(\rho\) values. The \(\rho\) values are used to calculate \(\omega\) value for performance of beta t-tests on the real data.

Usage

smbetattest(X, na, nb, alpha)

Arguments

X

simulated count data with N genes or isoforms.

na

number of replicate libraries in condition A.

nb

number of replicate libraries in condition B.

alpha

statistical probabilistic threshold, default is 0.05.

Value

Return a set of null \(\rho\) values.

Details

Before performing NBBttest on real data, user needs \(\omega\) value for the threshold of \(\rho\). To determine \(\omega\) value, user is requred to generate a set of null data having the same gene or isoform number and the same numbers of replicate libraries in two conditions and then performs beta t-test on the null datasets by setting \(\rho\) =1 and \(\omega\) =1. In current package, NBBttest can automatically perform the simulation of null data, multiple beta t-test to estimate \(\omega\).

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. DOI: 10.1371/journal.pone.0123658.

See Also

See Also as mbetattest

Examples

# NOT RUN {
data(skjt) 
nrho<-smbetattest(X=skjt[1:60,],na=3,nb=3,alpha=0.05)

# }