twilight (version 1.42.0)

twilight.getlambda: Internal function to compute regularization parameter lambda

Description

The SEP method optionally includes a penalty term in order to estimate the percentage of non-significant differences/genes.

Usage

twilight.getlambda(xin, verbose = TRUE)

Arguments

xin
A numerical vector containing $p$-values.
verbose
Logical value for message printing.

Value

Details

The function finds a suitable regularization parameter $\lambda$. For a sequence of lambdas, the objective function of SEP is computed for subsamples of the $p-value$ vector xin. The final estimate is chosen based upon a Wilcoxon test comparison between objective function values of $\lambda=0$ and each $\lambda>0$. The penalized objective function should not differ a lot from the unpenalized one. Therefore, the highest lambda that leads to a non-significant difference in means is chosen.

References

Scheid S and Spang R (2004): A stochastic downhill search algorithm for estimating the local false discovery rate, IEEE TCBB 1(3), 98--108.

Scheid S and Spang R (2005): twilight; a Bioconductor package for estimating the local false discovery rate, Bioinformatics 21(12), 2921--2922.

Scheid S and Spang R (2006): Permutation filtering: A novel concept for significance analysis of large-scale genomic data, in: Apostolico A, Guerra C, Istrail S, Pevzner P, and Waterman M (Eds.): Research in Computational Molecular Biology: 10th Annual International Conference, Proceedings of RECOMB 2006, Venice, Italy, April 2-5, 2006. Lecture Notes in Computer Science vol. 3909, Springer, Heidelberg, pp. 338-347.

See Also

twilight