Estimation of local false discovery rates
LocalFDR(dataf = dataf, graph = TRUE, method = NULL, lambda0 = 0.5,
smoothing = "1", thres = c(0.01, 0.05, 0.1, 0.2), mm = c(3, 5, 15, NA))input data file with two columns (1 = gene name, 2= ordered raw pvalues).
if TRUE a pdf graphic is created.
method for estimating m0. This must be one of the strings "adaptive", "conservative", "bootstap", "smoother" or NULL.
value used in calculating m0.
"1" for the initial published method, "2" for the PAVA method isotonic (monotonely increasing nonparametric) least squares regression - see P. Broberg (2005).
threshold defining intervals used for the movering average smoothing.
parameter defining intervals used for the movering average smoothing.
- if graph = TRUE, a file of graphics named LocalFDRGraph.pdf
- A data file (LocalFDRFile.txt) with 4 columns : gene name, raw pvalues and two columns corresponding to smoothed FDR values.
Aubert J, Bar-Hen A, Daudin J.J, Robin S (2004) Determination of the differentially expressed genes in microarrays experiments using local FDR, BMC Bioinformatics, 5:125.
Aubert J , Bar-Hen A, Daudin J.J, Robin S (2005) Correction: Determination of the differentially expressed genes in microarray experiments using local FDR, BMC Bioinformatics, 6:42.
Per Broberg (2005) A comparative review of estimates of the proportion unchanged genes and the false discovery rate, BMC Bioinformatics 6:199