ssizeRNA (version 1.1.2)

check.power: Average Power and True FDR Based on Voom and Limma Pipeline

Description

For the voom and limma pipeline method, when we control false discovery rate by using both Benjamini and Hochberg (1995) method and q-value procedure (Storey et al., 2004), check.power calculates average power and true FDR for given sample size, user-specified proportions of non-differentially expressed genes, number of iterations, FDR level to control, mean counts in control group, dispersion, and log fold change.

Usage

check.power(arg, k, fdr, mu, disp, logfc)

Arguments

arg

a list of global parameters to pass into the function, such as total number of genes, proportion of non-differentially expressed genes and treatment groups. See Details for more information.

k

number of iterations.

fdr

the false discovery rate to be controlled.

mu

a scalar of mean counts in control group from which to simulate.

disp

a scalar of dispersion parameter from which to simulate.

logfc

log fold change between treatment group and control group.

Value

• pow_bh_ave
  average power when controlling FDR by Benjamini and Hochberg (1995) method.
• fdr_bh_ave
  true false discovery rate when controlling FDR by Benjamini and Hochberg (1995) method.
• pow_bh_ave
  average power when controlling FDR by q-value procedure (Storey et al., 2004).
• fdr_bh_ave
  true false discovery rate when controlling FDR by q-value procedure (Storey et al., 2004).

Details

arg = list(nG, pi0, group) where nG is the total number of genes, pi0 is the proportion of non-differentially expressed genes, and group is the treatment groups.

References

Benjamini, Y. and Hochberg, Y. (1995) Controlling the false discovery rate: a practical and powerful approach to multiple testing. J. R. Stat. Soc. B, 57, 289-300.

Storey, J. D., Taylor, J. E. and Siegmund, D. (2004) Strong control, conservative point estimation and simultaneous rates: a unified approach. J. R. Stat. Soc. B, 66, 187- 205.

Examples

library(edgeR)
library(qvalue)
arg = list(
  nG = 10000,
  pi0 = 0.8,
  group = rep(c(1, 2), each = 13)
)

k <- 2                                   ## number of simulations (defined by user)
fdr <- 0.05                              ## the false discovery rate to be controlled
mu <- 10                                 ## mean counts in control group for all genes
disp <- 0.1                              ## dispersion for all genes
logfc <- log(2)                          ## log fold change for up-regulated genes

check.power(arg, k, fdr, mu, disp, logfc)