c212.TST {c212}R Documentation

Implementaion of the two-stage estimator (TST) for the proportion of true null hypotheses.

Description

The two-stage estimator (TST) is one of a number of estimators of the proportion of true null hypotheses. It uses the Benjamini-Hochberg procedure at a reduced level to make the estimate. This implementation assumes a grouped structure for the data.

Usage

c212.TST(trial.data, alpha)

Arguments

trial.data

Data frame containing the p-values for the hypotheses being tested. The data must contain the following columns: B: the index or name of the groupings; p: the p-values of the hypotheses.

alpha

The level for FDR control. E.g. 0.05.

Value

An estimate of the proportion of true null hypotheses.

Note

The implementation is that described in Hu, J. X. and Zhao, H. and Zhou, H. H. (2010).

Author(s)

R. Carragher<raymond.carragher@strath.ac.uk>

References

Hu, J. X. and Zhao, H. and Zhou, H. H. (2010). False Discovery Rate Control With Groups. J Am Stat Assoc, 105(491):1215-1227.

Y. Benjamini, A. M. Krieger, and D. Yekutieli (2006). Adaptive linear step-up procedures that control the false discovery rate. Biometrika, 93(3):491–507.

Examples

data(c212.FDR.data)
c212.TST(c212.FDR.data)
## Not run: 
          B pi0
1 Bdy-sys_5 1.0
2 Bdy-sys_6 1.0
3 Bdy-sys_7 1.0
4 Bdy-sys_8 1.0
5 Bdy-sys_2 0.5
6 Bdy-sys_3 0.0
7 Bdy-sys_4 1.0
8 Bdy-sys_1 1.0

## End(Not run)

[Package c212 version 0.98 Index]